# threat detection

Threat detection is a security strategy for identifying deviations from expected actions using collected, analyzed, and correlated data.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Mapping the AI threat landscape: MITRE ATLAS comes to Elastic Security

DevFeed: [Mapping the AI threat landscape: MITRE ATLAS comes to Elastic Security](<https://devfeed.tech/articles/mapping-the-ai-threat-landscape-mitre-atlas-comes-to-elastic-security-146683.md>)

Original publisher: [Read original article](<https://www.elastic.co/security-labs/blog/mitre-atlas-elastic-security-detection-coverage>)

Author: Davis Plumlee

Published: 2026-11-20T16:30:00Z

Content type: article

Language: en

Sources: [Elastic Security Labs](<https://devfeed.tech/sources/elastic-security-labs.md>)

Topics: [ai security](<https://devfeed.tech/topics/ai-security.md>), [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [Security](<https://devfeed.tech/topics/security.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [shadow AI](<https://devfeed.tech/topics/shadow-ai.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-automation](<https://devfeed.tech/tags/ai-automation.md>), [atlas](<https://devfeed.tech/tags/atlas.md>), [elastic](<https://devfeed.tech/tags/elastic.md>), [elastic-security](<https://devfeed.tech/tags/elastic-security.md>), [mitre](<https://devfeed.tech/tags/mitre.md>), [mitre-atlas](<https://devfeed.tech/tags/mitre-atlas.md>), [security](<https://devfeed.tech/tags/security.md>), [security-operations](<https://devfeed.tech/tags/security-operations.md>), [soc](<https://devfeed.tech/tags/soc.md>)

### AI overview

Elastic Security 9.6 adds MITRE ATLAS mappings alongside ATT&CK for prebuilt AI platform and GenAI detection rules, giving users a separate view of coverage for AI threats such as prompt injection, jailbreaks, stolen model API keys, and poisoned agent tools. Users can inspect coverage in a new table, add or edit both frameworks' mappings in rule creation workflows, and use Agent Builder to query covered threats or find rules for ATLAS techniques. A managed MITRE data service stores framework entities as Kibana Saved Objects and serves them through a data client and API, enabling queries and filtering and supporting multiple frameworks. Elastic says this may allow framework updates to follow the prebuilt-rule release cycle; the feature timing remains at its discretion.

### Source excerpt

Elastic Security 9.6 adds MITRE ATLAS to our detection rules and the tools you use to manage them, so you can see which AI attacks your rules already cover.

## LLM-Based Threat Detection and Prevention Framework for IoT Ecosystems

DevFeed: [LLM-Based Threat Detection and Prevention Framework for IoT Ecosystems](<https://devfeed.tech/articles/llm-based-threat-detection-and-prevention-framework-for-iot-ecosystems-144852.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2505.00240>)

Author: Yazan Otoum, Arghavan Asad, Ishtiaq Ahmad, Amiya Nayak

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [Internet of things](<https://devfeed.tech/topics/iot.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [3](<https://devfeed.tech/tags/3.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [actions](<https://devfeed.tech/tags/actions.md>), [adaptive](<https://devfeed.tech/tags/adaptive.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [bert](<https://devfeed.tech/tags/bert.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-et](<https://devfeed.tech/tags/cs-et.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [detection](<https://devfeed.tech/tags/detection.md>), [docker](<https://devfeed.tech/tags/docker.md>), [ecosystems](<https://devfeed.tech/tags/ecosystems.md>), [edge-cloud](<https://devfeed.tech/tags/edge-cloud.md>), [experimental](<https://devfeed.tech/tags/experimental.md>), [f1](<https://devfeed.tech/tags/f1.md>), [framework](<https://devfeed.tech/tags/framework.md>), [iot](<https://devfeed.tech/tags/iot.md>), [llm](<https://devfeed.tech/tags/llm.md>), [threat](<https://devfeed.tech/tags/threat.md>), [threat-detection](<https://devfeed.tech/tags/threat-detection.md>)

### AI overview

The proposed IoT security framework pairs a detection component with a prevention component: fine-tuned models trained on IoT-23 and TON_IoT identify anomalous network behavior, while a Prevention LLM selects mitigation actions. Prompt management, local adaptation, and global refinement support context-aware decisions and ongoing model-guided adaptation. In Docker-based edge-cloud experiments, BERT Small reportedly achieved 99.75% accuracy, F1-score, precision, and recall for threat detection; the Prevention LLM achieved 98.3% accuracy in selecting suitable mitigations. These are reported experimental results, and the supplied abstract does not describe broader deployment or validation.

### Source excerpt

arXiv:2505.00240v3 Announce Type: replace-cross Abstract: The rapid expansion of the Internet of Things (IoT) has introduced complex and evolving cybersecurity challenges. This paper presents a Large Language Model (LLM)-based framework for intelligent threat detection and prevention in IoT networks. The proposed architecture integrates two core components: a Detection Component that leverages fine-tuned models trained on IoT-specific datasets (IoT-23 and TON_IoT) to identify anomalous network behaviours, and a Prevention Component that generates adaptive response strategies to mitigate detected threats. The framework incorporates prompt management, local adaptation, and global refinement modules to support context-aware decision-making and continuous model-guided adaptation. Experimental validation in a Docker-based edge-cloud environment shows that BERT Small achieves 99.75% accuracy, F1-score, precision, and recall for threat detection, while the Prevention LLM achieves 98.3% accuracy in selecting suitable mitigation actions. These results highlight the potential of LLM-driven architectures to provide explainable and adaptive security solutions for next-generation IoT ecosystems.

## Behavioral Integrity Verification for AI Agent Skills

DevFeed: [Behavioral Integrity Verification for AI Agent Skills](<https://devfeed.tech/articles/behavioral-integrity-verification-for-ai-agent-skills-145331.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2605.11770>)

Author: Yuhao Wu, Tung-Ling Li, Hongliang Liu

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [threat detection](<https://devfeed.tech/topics/threat-detection.md>)

Tags: [adversarial](<https://devfeed.tech/tags/adversarial.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-skills](<https://devfeed.tech/tags/agent-skills.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agent-skills](<https://devfeed.tech/tags/ai-agent-skills.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [attack](<https://devfeed.tech/tags/attack.md>), [attack-chains](<https://devfeed.tech/tags/attack-chains.md>), [auditing](<https://devfeed.tech/tags/auditing.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [capability](<https://devfeed.tech/tags/capability.md>), [categories](<https://devfeed.tech/tags/categories.md>), [cause](<https://devfeed.tech/tags/cause.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-sy](<https://devfeed.tech/tags/cs-sy.md>), [eess-sy](<https://devfeed.tech/tags/eess-sy.md>), [integrity](<https://devfeed.tech/tags/integrity.md>), [skills](<https://devfeed.tech/tags/skills.md>), [verification](<https://devfeed.tech/tags/verification.md>)

### AI overview

Behavioral integrity verification (BIV) checks whether an AI agent skill's declared capabilities match what its code and instructions enable. It pairs deterministic code analysis with LLM-assisted capability extraction over a shared taxonomy, producing evidence for deviation analysis, root-cause classification, and malicious-skill detection. In 49,943 OpenClaw skills, 80.0% had at least one classified deviation; the authors attributed 81.1% of deviations to developer oversight and 18.9% to adversarial intent, and predicted multi-stage attack chains in 5.0% of skills. On a separate 906-skill benchmark, BIV achieved an F1 of 0.949, outperforming the reported rule-based and single-pass LLM baselines. These are results reported in the supplied abstract.

### Source excerpt

arXiv:2605.11770v2 Announce Type: replace-cross Abstract: Agent skills extend LLM agents with privileged third-party capabilities such as filesystem access, credentials, network calls, and shell execution. Existing safety work catches malicious prompts and risky runtime actions, but the skill artifact itself goes unverified. We formalize this as the behavioral integrity verification (BIV) problem: a typed set comparison between declared and actual capabilities over a shared taxonomy that bridges code, instructions, and metadata. The BIV framework instantiates this comparison by pairing deterministic code analysis with LLM-assisted capability extraction. The resulting structured evidence supports three downstream analyses: deviation taxonomy, root-cause classification, and malicious-skill detection. On 49,943 skills from the OpenClaw registry, the deviation taxonomy reveals a pervasive description-implementation gap: 80.0% of skills have at least one deviation in the taxonomy, with four compound-threat categories surfaced. Root-cause classification finds that deviations are mostly oversight, not malice: 81.1% trace to developer oversight and 18.9% to adversarial intent, with 5.0% of skills carrying predicted multi-stage attack chains. On a 906-skill malicious-skill detection benchmark, BIV reaches an F1 of 0.949, outperforming state-of-the-art rule-based and single-pass LLM baselines. These results demonstrate behavioral integrity auditing for agent skills at scale.

## How AWS Security Incident Response triages your security findings

DevFeed: [How AWS Security Incident Response triages your security findings](<https://devfeed.tech/articles/how-aws-security-incident-response-triages-your-security-findings-144385.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/security/how-aws-security-incident-response-triages-your-security-findings/>)

Author: Anatoliy Kochetov

Published: 2026-11-19T19:20:58Z

Content type: article

Language: en

Sources: [AWS Security Blog](<https://devfeed.tech/sources/aws-security-blog.md>)

Topics: [alert triage](<https://devfeed.tech/topics/alert-triage.md>), [Amazon GuardDuty](<https://devfeed.tech/topics/amazon-guardduty.md>), [AWS Security Hub](<https://devfeed.tech/topics/aws-security-hub.md>), [Incident response](<https://devfeed.tech/topics/incident-response.md>), [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [AWS CloudTrail](<https://devfeed.tech/topics/aws-cloudtrail.md>), [Amazon EventBridge](<https://devfeed.tech/topics/amazon-eventbridge.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [amazon-ec2](<https://devfeed.tech/tags/amazon-ec2.md>), [amazon-elastic-compute-cloud-amazon-ec2](<https://devfeed.tech/tags/amazon-elastic-compute-cloud-amazon-ec2.md>), [amazon-eventbridge](<https://devfeed.tech/tags/amazon-eventbridge.md>), [amazon-guardduty](<https://devfeed.tech/tags/amazon-guardduty.md>), [amazon-s3](<https://devfeed.tech/tags/amazon-s3.md>), [amazon-simple-storage-service-amazon-s3](<https://devfeed.tech/tags/amazon-simple-storage-service-amazon-s3.md>), [archiving](<https://devfeed.tech/tags/archiving.md>), [automated](<https://devfeed.tech/tags/automated.md>), [automation](<https://devfeed.tech/tags/automation.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-cloudtrail](<https://devfeed.tech/tags/aws-cloudtrail.md>), [aws-identity-and-access-management-iam](<https://devfeed.tech/tags/aws-identity-and-access-management-iam.md>), [aws-management-console](<https://devfeed.tech/tags/aws-management-console.md>), [aws-security-hub](<https://devfeed.tech/tags/aws-security-hub.md>), [aws-support](<https://devfeed.tech/tags/aws-support.md>), [cspm](<https://devfeed.tech/tags/cspm.md>), [incident-response](<https://devfeed.tech/tags/incident-response.md>), [security](<https://devfeed.tech/tags/security.md>), [security-blog](<https://devfeed.tech/tags/security-blog.md>), [security-findings](<https://devfeed.tech/tags/security-findings.md>), [security-identity-compliance](<https://devfeed.tech/tags/security-identity-compliance.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>)

### AI overview

AWS Security Incident Response triages active-threat findings from GuardDuty and eligible third-party detections sent to Security Hub CSPM; posture and compliance findings remain for the customer to address. It evaluates finding data alongside CloudTrail and VPC Flow Logs, threat intelligence, and environmental context. Benign findings are archived in GuardDuty; uncertain or concerning activity can lead to a proactive case, while posture findings stay Current without a case. Third-party findings use Security Hub workflow statuses: NEW to NOTIFIED during triage, then SUPPRESSED if cleared as benign. The service learns known-good patterns over time and can reassess them when context changes. The dashboard tracks ingestion through escalation, monthly reports detail investigations and learned context, and GuardDuty's Archived filter offers another check. The text says fewer than 1% of ingested findings result in customer-facing escalation.

### Source excerpt

AWS Security Incident Response continuously triages the threat findings from Amazon GuardDuty and AWS Security Hub CSPM, but most of that work never shows up as a case. If cases are all you look at, it's hard to tell whether the service is working at all, and that's the question I hear most often when [...]

## What Is Preemptive MDR? A Guide For Security Leaders

DevFeed: [What Is Preemptive MDR? A Guide For Security Leaders](<https://devfeed.tech/articles/what-is-preemptive-mdr-a-guide-for-security-leaders-144829.md>)

Original publisher: [Read original article](<https://www.rapid7.com/blog/post/dr-what-is-preemptive-mdr-security-leaders-guide>)

Author: Emma Burdett

Published: 2026-11-19T15:58:53Z

Content type: article

Language: en

Sources: [Rapid7 Cybersecurity](<https://devfeed.tech/sources/rapid7-cybersecurity-blog.md>)

Topics: [Exposure Management](<https://devfeed.tech/topics/exposure-management.md>), [Incident response](<https://devfeed.tech/topics/incident-response.md>), [vulnerability management](<https://devfeed.tech/topics/vulnerability-management.md>), [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [human review](<https://devfeed.tech/topics/human-review.md>)

Tags: [active-exploitation](<https://devfeed.tech/tags/active-exploitation.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assisted](<https://devfeed.tech/tags/ai-assisted.md>), [analysts](<https://devfeed.tech/tags/analysts.md>), [application](<https://devfeed.tech/tags/application.md>), [assets](<https://devfeed.tech/tags/assets.md>), [attack](<https://devfeed.tech/tags/attack.md>), [business](<https://devfeed.tech/tags/business.md>), [compromise](<https://devfeed.tech/tags/compromise.md>), [contain](<https://devfeed.tech/tags/contain.md>), [context](<https://devfeed.tech/tags/context.md>), [critical](<https://devfeed.tech/tags/critical.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [cybersecurity-company](<https://devfeed.tech/tags/cybersecurity-company.md>), [detection](<https://devfeed.tech/tags/detection.md>), [detection-and-response](<https://devfeed.tech/tags/detection-and-response.md>), [exploitation](<https://devfeed.tech/tags/exploitation.md>), [exposure-assessment-platform](<https://devfeed.tech/tags/exposure-assessment-platform.md>), [exposure-management](<https://devfeed.tech/tags/exposure-management.md>), [guide](<https://devfeed.tech/tags/guide.md>), [managed-detection-and-response](<https://devfeed.tech/tags/managed-detection-and-response.md>), [managed-detection-and-response-mdr](<https://devfeed.tech/tags/managed-detection-and-response-mdr.md>), [managed-security-solutions](<https://devfeed.tech/tags/managed-security-solutions.md>), [mdr](<https://devfeed.tech/tags/mdr.md>), [mdr-must-haves](<https://devfeed.tech/tags/mdr-must-haves.md>), [security](<https://devfeed.tech/tags/security.md>), [vulnerability-management](<https://devfeed.tech/tags/vulnerability-management.md>), [what-is](<https://devfeed.tech/tags/what-is.md>)

### AI overview

Rapid7 describes preemptive MDR as connecting asset and vulnerability exposure context with threat intelligence, threat hunting, investigation, and response. Analysts use factors such as internet exposure, business criticality, and active exploitation to prioritize investigation and remediation; findings feed back into detection rules and hunting priorities, with ownership tracked through follow-up. AI can gather and correlate evidence and run parts of an investigation in parallel, but missing identity or asset data can leave gaps. Human analysts validate findings and weigh response consequences, such as disrupting a critical service. The article advises security leaders to ask providers to show how exposure context changes investigations, how identified weaknesses are assigned and addressed, what AI does and how it is overseen, and how responsibilities and approval for response actions are set. It says Rapid7 MDR includes unlimited incident response; progress should be reviewed through case evidence, including outstanding work.

### Source excerpt

When an MDR provider contains a compromised endpoint, your team needs to know whether the weakness that enabled the attack exists elsewhere and who is responsible for addressing it. Without that follow-through, the immediate incident may be resolved while another attacker still has a way in. Preemptive managed detection and response (MDR) is Rapid7's approach to connecting exposure context, threat intelligence, AI-assisted investigation, and human expertise. It supports proactive cybersecurity by helping teams prioritize weaknesses before exploitation, investigate threats with a clearer understanding of risk, and use their findings to strengthen defenses. How does preemptive MDR differ from traditional MDR? Managed detection and response provides security specialists who monitor, investigate, and respond to threats around the clock. Many services also include proactive threat hunting and recommendations to improve security. Preemptive MDR connects that work more directly to what makes an organization vulnerable. When analysts investigate suspicious activity on a server, knowing that it is internet-facing, supports a critical application, and has a vulnerability under active exploitation helps them assess urgency and determine where to look next. In Rapid7's model, exposure findings inform investigation and remediation priorities, while investigations reveal weaknesses that need attention. Security leaders gain a clearer connection between the threats their provider handles and the conditions their organization needs to address. Within a broader preemptive cybersecurity strategy, MDR connects exposure information with the people investigating and responding to threats. The aim is to reduce opportunities for compromise and intervene before an attack causes harm, while retaining the expertise to contain and recover from incidents. How exposure context and proactive threat hunting inform MDR By combining information about assets, vulnerabilities, business criticality, a

## Fig Announces Elastic Integration to Help Security Teams Protect Detection Coverage as Data Changes

DevFeed: [Fig Announces Elastic Integration to Help Security Teams Protect Detection Coverage as Data Changes](<https://devfeed.tech/articles/fig-announces-elastic-integration-to-help-security-teams-protect-detection-coverage-as-data-changes-143905.md>)

Original publisher: [Read original article](<https://hackernoon.com/fig-announces-elastic-integration-to-help-security-teams-protect-detection-coverage-as-data-changes?source=rss>)

Author: Kevin John

Published: 2026-11-19T14:09:46Z

Content type: news

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [Security Information and Event Management (SIEM)](<https://devfeed.tech/topics/siem-security.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [versioning](<https://devfeed.tech/topics/versioning.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [api](<https://devfeed.tech/tags/api.md>), [changes](<https://devfeed.tech/tags/changes.md>), [coverage](<https://devfeed.tech/tags/coverage.md>), [data](<https://devfeed.tech/tags/data.md>), [dependencies](<https://devfeed.tech/tags/dependencies.md>), [detection](<https://devfeed.tech/tags/detection.md>), [detection-as-code](<https://devfeed.tech/tags/detection-as-code.md>), [detection-coverage](<https://devfeed.tech/tags/detection-coverage.md>), [detection-coverage-validation](<https://devfeed.tech/tags/detection-coverage-validation.md>), [detection-engineering](<https://devfeed.tech/tags/detection-engineering.md>), [detection-rule-drift](<https://devfeed.tech/tags/detection-rule-drift.md>), [elastic](<https://devfeed.tech/tags/elastic.md>), [elastic-security](<https://devfeed.tech/tags/elastic-security.md>), [integration](<https://devfeed.tech/tags/integration.md>), [map](<https://devfeed.tech/tags/map.md>), [migrations](<https://devfeed.tech/tags/migrations.md>), [secops](<https://devfeed.tech/tags/secops.md>), [secops-cicd](<https://devfeed.tech/tags/secops-cicd.md>), [security](<https://devfeed.tech/tags/security.md>), [security-data-lineage](<https://devfeed.tech/tags/security-data-lineage.md>), [security-data-pipelines](<https://devfeed.tech/tags/security-data-pipelines.md>), [siem-migrations](<https://devfeed.tech/tags/siem-migrations.md>), [teams](<https://devfeed.tech/tags/teams.md>)

### AI overview

Fig's Elastic Security integration maps data sources through pipelines, mappings and fields to the detection rules that depend on them. Using a read-only API key, Fig retrieves Elastic configuration and identifies detections affected when upstream data changes, pinpoints breaks and recommends fixes. Teams can test changes against their own data before production, then ship validated changes as code through CI/CD with version control and one-click rollback. For migrations to Elastic, Elastic Automatic Migration translates existing rules; Fig checks them against destination data before cutover and flags rules needing rework. Elastic provides its platform and prebuilt integrations and rules, while Fig focuses on data dependencies and change validation.

### Source excerpt

Fig announces an Elastic Security integration to help SecOps teams map data dependencies, validate detection changes, and protect coverage during migrations.

## Exclusive: Fig Security partners with Elastic to show how data changes affect detection coverage

DevFeed: [Exclusive: Fig Security partners with Elastic to show how data changes affect detection coverage](<https://devfeed.tech/articles/exclusive-fig-security-partners-with-elastic-to-show-how-data-changes-affect-detection-coverage-143693.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/11/19/exclusive-fig-security-partners-with-elastic-to-show-how-data-changes-affect-detection-coverage/>)

Author: Duncan Riley

Published: 2026-11-19T14:00:04Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Security Information and Event Management (SIEM)](<https://devfeed.tech/topics/siem-security.md>), [Security](<https://devfeed.tech/topics/security.md>)

Tags: [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [automatic-import](<https://devfeed.tech/tags/automatic-import.md>), [automatic-migration](<https://devfeed.tech/tags/automatic-migration.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [changes](<https://devfeed.tech/tags/changes.md>), [continuous-delivery](<https://devfeed.tech/tags/continuous-delivery.md>), [continuous-integration](<https://devfeed.tech/tags/continuous-integration.md>), [coverage](<https://devfeed.tech/tags/coverage.md>), [data](<https://devfeed.tech/tags/data.md>), [dependencies](<https://devfeed.tech/tags/dependencies.md>), [detection](<https://devfeed.tech/tags/detection.md>), [detection-coverage](<https://devfeed.tech/tags/detection-coverage.md>), [detection-rules](<https://devfeed.tech/tags/detection-rules.md>), [drift](<https://devfeed.tech/tags/drift.md>), [elastic](<https://devfeed.tech/tags/elastic.md>), [elastic-security](<https://devfeed.tech/tags/elastic-security.md>), [fig-security](<https://devfeed.tech/tags/fig-security.md>), [gal-shafir](<https://devfeed.tech/tags/gal-shafir.md>), [google-cloud-security](<https://devfeed.tech/tags/google-cloud-security.md>), [integration](<https://devfeed.tech/tags/integration.md>), [integrations](<https://devfeed.tech/tags/integrations.md>), [jamie-hynds](<https://devfeed.tech/tags/jamie-hynds.md>), [mapping](<https://devfeed.tech/tags/mapping.md>), [news](<https://devfeed.tech/tags/news.md>), [nir-loya-dahan](<https://devfeed.tech/tags/nir-loya-dahan.md>), [operations](<https://devfeed.tech/tags/operations.md>), [partners](<https://devfeed.tech/tags/partners.md>), [partnership](<https://devfeed.tech/tags/partnership.md>), [platform](<https://devfeed.tech/tags/platform.md>), [roy-haimof](<https://devfeed.tech/tags/roy-haimof.md>), [secops](<https://devfeed.tech/tags/secops.md>), [security](<https://devfeed.tech/tags/security.md>), [security-data-lineage](<https://devfeed.tech/tags/security-data-lineage.md>), [security-information-and-event-management](<https://devfeed.tech/tags/security-information-and-event-management.md>), [security-operations](<https://devfeed.tech/tags/security-operations.md>), [startup](<https://devfeed.tech/tags/startup.md>), [team8](<https://devfeed.tech/tags/team8.md>), [ten-eleven-ventures](<https://devfeed.tech/tags/ten-eleven-ventures.md>), [the-latest](<https://devfeed.tech/tags/the-latest.md>)

### AI overview

Fig Security's integration with Elastic Security maps data sources through pipelines, mappings, and fields to the detection rules that depend on them. Fig says it identifies rules affected by data changes and suggests repairs, helping teams detect coverage gaps even when rules remain active. Teams can test changes against their own environment and ship them as code with CI/CD, version control, and one-click rollback. For migrations, Fig checks rules translated by Elastic Automatic Migration against available Elastic data and flags rules needing rework with recommended fixes. The article describes the integration as available now; these capabilities are presented as company claims.

### Source excerpt

Security operations startup Fig Security Inc. today announced an integration partnership with Elastic N.V. that it says gives security teams visibility into how data changes affect their detection coverage. The partnership sees Fig's capabilities for mapping detection dependencies now integrating with Elastic Security, the open security operations platform from Elastic. The platform offers prebuilt integrations [...] The post Exclusive: Fig Security partners with Elastic to show how data changes affect detection coverage appeared first on SiliconANGLE.

## Cry2Wolf: Not Every Branded Bug Deserves a Fire Drill

DevFeed: [Cry2Wolf: Not Every Branded Bug Deserves a Fire Drill](<https://devfeed.tech/articles/cry2wolf-not-every-branded-bug-deserves-a-fire-drill-144475.md>)

Original publisher: [Read original article](<https://www.ox.security/blog/cry2wolf-not-every-branded-bug-deserves-a-fire-drill/>)

Author: Moshe Siman Tov Bustan

Published: 2026-11-19T11:21:39Z

Content type: opinion

Language: en

Sources: [OX Security](<https://devfeed.tech/sources/ox-security.md>)

Topics: [alert triage](<https://devfeed.tech/topics/alert-triage.md>), [Security](<https://devfeed.tech/topics/security.md>), [threat detection](<https://devfeed.tech/topics/threat-detection.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-vibesec](<https://devfeed.tech/tags/ai-vibesec.md>), [application-security](<https://devfeed.tech/tags/application-security.md>), [attack](<https://devfeed.tech/tags/attack.md>), [attack-surface](<https://devfeed.tech/tags/attack-surface.md>), [block](<https://devfeed.tech/tags/block.md>), [bug](<https://devfeed.tech/tags/bug.md>), [checklist](<https://devfeed.tech/tags/checklist.md>), [credentials](<https://devfeed.tech/tags/credentials.md>), [critical-infrastructure](<https://devfeed.tech/tags/critical-infrastructure.md>), [disclosure](<https://devfeed.tech/tags/disclosure.md>), [ox-security](<https://devfeed.tech/tags/ox-security.md>), [research](<https://devfeed.tech/tags/research.md>), [security](<https://devfeed.tech/tags/security.md>), [software-supply-chain-security](<https://devfeed.tech/tags/software-supply-chain-security.md>), [thought-leadership](<https://devfeed.tech/tags/thought-leadership.md>), [vulnerability](<https://devfeed.tech/tags/vulnerability.md>)

### AI overview

The excerpt argues that branded vulnerability alerts should be triaged by evidence and practical exposure, because disproportionate emergency response drains capacity and can lead teams to ignore genuine threats. It contrasts PHP2Shell, described as exploited before disclosure, with Java4Shell and NGINX2Root, for which it reports no confirmed in-the-wild exploitation and notes that proofs of concept do not establish practical exploitation. For Java4Shell, the excerpt lists narrow hardware, software and application conditions, heap control, timing, and crash risk; OX Research estimates fewer than 0.12% of JVMs are at remote code execution risk. Its checklist weighs exploitation evidence, exploit reliability and scope, preconditions, organizational exposure, mitigations, attacker effort, and who is making the claim. It recommends proportionate patching and basic risk reduction such as disabling unused HTTP/2, configuring WAFs, and restricting internet access to critical infrastructure. It cautions that assessments change with evidence and that absence of observed exploitation does not prove safety.

### Source excerpt

Security teams are burning out on vulnerability hype. Here's how to tell a real threat from a nothingburger. Every few days, sometimes every few hours, a new vulnerability arrives with a name, a logo, and a countdown clock. The headlines call it critical. The vendor emails follow within the hour. Security teams drop their roadmaps [...] The post Cry2Wolf: Not Every Branded Bug Deserves a Fire Drill appeared first on OX Security.

## Smoothing and Learning for Movement-Robust RSS-Based Spoofing Detection

DevFeed: [Smoothing and Learning for Movement-Robust RSS-Based Spoofing Detection](<https://devfeed.tech/articles/smoothing-and-learning-for-movement-robust-rss-based-spoofing-detection-143139.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23854>)

Author: Usama Mir

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [spoofing](<https://devfeed.tech/topics/spoofing.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>)

Tags: [attack](<https://devfeed.tech/tags/attack.md>), [classifier](<https://devfeed.tech/tags/classifier.md>), [community-detection](<https://devfeed.tech/tags/community-detection.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [detection](<https://devfeed.tech/tags/detection.md>), [features](<https://devfeed.tech/tags/features.md>), [filter](<https://devfeed.tech/tags/filter.md>), [gaussian](<https://devfeed.tech/tags/gaussian.md>), [learning](<https://devfeed.tech/tags/learning.md>), [median](<https://devfeed.tech/tags/median.md>), [network](<https://devfeed.tech/tags/network.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [region](<https://devfeed.tech/tags/region.md>), [robust](<https://devfeed.tech/tags/robust.md>), [rss](<https://devfeed.tech/tags/rss.md>), [scheme](<https://devfeed.tech/tags/scheme.md>), [score](<https://devfeed.tech/tags/score.md>), [sequence](<https://devfeed.tech/tags/sequence.md>), [sequences](<https://devfeed.tech/tags/sequences.md>), [signal](<https://devfeed.tech/tags/signal.md>), [spoofing](<https://devfeed.tech/tags/spoofing.md>)

### AI overview

The study improves a movement-robust RSS spoofing detector in two ways: it smooths position-change detector (PCD) scores with median or Gaussian filters before thresholding, and replaces a fixed decision threshold with a supervised classifier using six features of community-detection region sequences. On indoor measurements from 52 transmitter locations, Gaussian smoothing raises PCD accuracy from 0.870 to 0.921 with training on 10 locations, and from 0.905 to 0.925 with training on 40. On 1,679 held-out synthetic attack and no-attack sequences built from those measurements, XGBoost achieves 0.949 accuracy and 0.940 F1; random forests achieve 0.99 AUC. The detector separates static attackers almost perfectly, but misses about one third of attacks where two transmitters move simultaneously, because their region sequences resemble those of one moving user.

### Source excerpt

arXiv:2611.23854v1 Announce Type: new Abstract: Physical-layer spoofing detection identifies an attacker who impersonates a legitimate wireless user by checking whether transmissions claiming the same identity originate from different locations, using the received signal strength (RSS) measured at several receivers. A recent scheme by Romero et al. makes this approach robust to user movement by combining a neural-network position-change detector (PCD) with community detection on a graph of frames and a fixed threshold on a hand-crafted test statistic. I study two modifications to this scheme. First, I smooth the sequence of PCD scores with a median or Gaussian temporal filter before thresholding. Second, I replace the fixed decision threshold with a supervised classifier operating on six statistical features of the region sequence produced by community detection. On real indoor RSS measurements from 52 transmitter locations, Gaussian filtering raises PCD accuracy from 0.870 to 0.921 when the PCD is trained on 10 locations and from 0.905 to 0.925 when trained on 40. On synthetic attack and no-attack sequences built from the same measurements, evaluated on a held-out test set of 1,679 sequences, the best classifier (XGBoost) reaches an accuracy of 0.949 and an F1 score of 0.940, and random forests reach an AUC of 0.99. The detector separates static attackers almost perfectly but misses about a third of attacks in which two transmitters move simultaneously, which produce region sequences similar to those of a single moving user.

## Rented Oscillations: Multi-Tenant Data Center Workload Synchronization Attacks and Mitigation

DevFeed: [Rented Oscillations: Multi-Tenant Data Center Workload Synchronization Attacks and Mitigation](<https://devfeed.tech/articles/rented-oscillations-multi-tenant-data-center-workload-synchronization-attacks-and-mitigation-143127.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23666>)

Author: Zaint A. Alexakis, Li Zhou, S. Gokul Krishnan, Charalambos Konstantinou

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [Resilience](<https://devfeed.tech/topics/resilience.md>), [synchronization](<https://devfeed.tech/topics/synchronization.md>), [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [attacks](<https://devfeed.tech/tags/attacks.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-sy](<https://devfeed.tech/tags/cs-sy.md>), [data-center](<https://devfeed.tech/tags/data-center.md>), [detection](<https://devfeed.tech/tags/detection.md>), [eess-sy](<https://devfeed.tech/tags/eess-sy.md>), [energy](<https://devfeed.tech/tags/energy.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [hardware-in-the-loop](<https://devfeed.tech/tags/hardware-in-the-loop.md>), [large-language-model](<https://devfeed.tech/tags/large-language-model.md>), [llm-training](<https://devfeed.tech/tags/llm-training.md>), [mitigation](<https://devfeed.tech/tags/mitigation.md>), [multi-tenant](<https://devfeed.tech/tags/multi-tenant.md>), [network](<https://devfeed.tech/tags/network.md>), [power](<https://devfeed.tech/tags/power.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [supercomputer](<https://devfeed.tech/tags/supercomputer.md>), [synchronization](<https://devfeed.tech/tags/synchronization.md>), [threat](<https://devfeed.tech/tags/threat.md>), [training](<https://devfeed.tech/tags/training.md>), [transmission](<https://devfeed.tech/tags/transmission.md>), [workstations](<https://devfeed.tech/tags/workstations.md>)

### AI overview

The paper finds that synchronized or naturally interacting data-center workloads can produce periodic power oscillations that stress the grid. Experiments characterize workload periodicity and support a hardware-grounded threat model; network analysis shows that megawatt-scale oscillations can saturate generator control limiters and amplify their effects, while Floquet analysis identifies a lightly damped mode near the forcing frequency. The authors propose detecting oscillations by signal energy and mitigating them by retiming workloads to reduce facility oscillatory energy. They validate the approach with power hardware-in-the-loop experiments and real-time simulations on a surrogate Saudi Arabian transmission network.

### Source excerpt

arXiv:2611.23666v1 Announce Type: cross Abstract: Multi-tenant data center (DC) facilities rent computing capacity on demand, placing controllable load within reach of anyone willing to pay for it. This paper considers a stealthy adversary who rents workstations and runs deliberately unoptimized large language model (LLM) training, synchronizing their consumption into large periodic oscillations while each workload remains individually indistinguishable from benign training. The periodicity of such workloads is characterized experimentally and used to model facility consumption, showing that oscillations emerge from the interaction of concurrent workloads, whether aligned by an adversary or arising naturally. A combined small- and large-signal assessment, under a hardware-grounded threat model whose feasibility is supported by experiments on a supercomputer, locates the oscillatory weak points of the network. MW-scale oscillations are shown to saturate the generators' control limiters, amplifying their effect, while Floquet analysis reveals a lightly damped mode emerging near the forcing frequency. To counter both origins, signal-energy-based detection and mitigation are proposed, the latter re-timing the workloads to minimize the facility's oscillatory energy. The approach is validated through power hardware-in-the-loop (PHIL) experiments and real-time simulations on a surrogate model of the Saudi Arabian transmission network.

## Ransomware Reaches Record Highs in Q3 2026 as the Threat Landscape Fragments

DevFeed: [Ransomware Reaches Record Highs in Q3 2026 as the Threat Landscape Fragments](<https://devfeed.tech/articles/ransomware-reaches-record-highs-in-q3-2026-as-the-threat-landscape-fragments-141214.md>)

Original publisher: [Read original article](<https://blog.checkpoint.com/security/ransomware-reaches-record-highs-in-q3-2026-as-the-threat-landscape-fragments/>)

Author: raphaelge@checkpoint.com

Published: 2026-11-18T13:00:18Z

Content type: article

Language: en

Sources: [Check Point Blog](<https://devfeed.tech/sources/check-point-blog.md>)

Topics: [Endpoint security](<https://devfeed.tech/topics/endpoint-security.md>), [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [Vulnerabilities](<https://devfeed.tech/topics/vulnerabilities.md>), [Resilience](<https://devfeed.tech/topics/resilience.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-security](<https://devfeed.tech/tags/ai-security.md>), [akira](<https://devfeed.tech/tags/akira.md>), [attack](<https://devfeed.tech/tags/attack.md>), [attack-paths](<https://devfeed.tech/tags/attack-paths.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [berlin](<https://devfeed.tech/tags/berlin.md>), [block](<https://devfeed.tech/tags/block.md>), [browsers](<https://devfeed.tech/tags/browsers.md>), [ecosystem](<https://devfeed.tech/tags/ecosystem.md>), [extortion](<https://devfeed.tech/tags/extortion.md>), [fragments](<https://devfeed.tech/tags/fragments.md>), [groups](<https://devfeed.tech/tags/groups.md>), [operators](<https://devfeed.tech/tags/operators.md>), [organizations](<https://devfeed.tech/tags/organizations.md>), [q3](<https://devfeed.tech/tags/q3.md>), [ransomware](<https://devfeed.tech/tags/ransomware.md>), [research](<https://devfeed.tech/tags/research.md>), [security](<https://devfeed.tech/tags/security.md>), [threat](<https://devfeed.tech/tags/threat.md>), [threat-intelligence](<https://devfeed.tech/tags/threat-intelligence.md>), [top-ten](<https://devfeed.tech/tags/top-ten.md>)

### AI overview

Q3 2026 set a record with 2,830 published ransomware victims as activity spread across 117 brands; the top ten groups accounted for just 49%, down from 58% in Q2. Qilin led with 366 victims, while LockBit fell out of the top ten. The United States represented 42% of observed victims, and Business Services was the largest industry category at 34%; the report cautions that sector figures do not establish deliberate targeting. Payment trends diverged: the average fell 45% quarter over quarter to just over $1 million, while the median rose 167% to $400,000. Several major organizations reportedly rejected demands, though stolen data was still published in some cases. The report urges teams to defend common attack paths, limit attacker access after compromise, prepare for data theft as well as encryption, and plan for the consequences of refusing payment.

### Source excerpt

The State of Ransomware Q3 2026 reveals a combination the ransomware market has not seen before: record victim numbers alongside record-low concentration among its leading groups. More ransomware brands claimed victims, the top ten fell below half of observed activity, and several high-profile organizations rejected major extortion demands. Together, these shifts reveal a ransomware ecosystem growing in volume, spreading across more operators, and facing changes in how victims respond to extortion. Key takeaways Q3 reached a record 2,830 victims, including 964 in July, 1,042 in August and 824 in September. 117 ransomware brands claimed victims, up from 91 in Q2, [...] The post Ransomware Reaches Record Highs in Q3 2026 as the Threat Landscape Fragments appeared first on Check Point Blog.

## Vulnerability Threat Sweep: New Vulnerabilities, Checked Against What You Actually Run

DevFeed: [Vulnerability Threat Sweep: New Vulnerabilities, Checked Against What You Actually Run](<https://devfeed.tech/articles/vulnerability-threat-sweep-new-vulnerabilities-checked-against-what-you-actually-run-141197.md>)

Original publisher: [Read original article](<https://logz.io/blog/vulnerability-threat-sweep/>)

Author: David Lotan Bolotnikoff

Published: 2026-11-18T12:34:46Z

Content type: article

Language: en

Sources: [Logz](<https://devfeed.tech/sources/logz.md>)

Topics: [vulnerability management](<https://devfeed.tech/topics/vulnerability-management.md>), [Vulnerabilities](<https://devfeed.tech/topics/vulnerabilities.md>), [Threat monitoring](<https://devfeed.tech/topics/threat-monitoring.md>), [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [known exploitable vulnerabilities](<https://devfeed.tech/topics/known-exploitable-vulnerabilities.md>)

Tags: [2025](<https://devfeed.tech/tags/2025.md>), [2026](<https://devfeed.tech/tags/2026.md>), [account](<https://devfeed.tech/tags/account.md>), [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [alert](<https://devfeed.tech/tags/alert.md>), [alerts](<https://devfeed.tech/tags/alerts.md>), [attack](<https://devfeed.tech/tags/attack.md>), [blog](<https://devfeed.tech/tags/blog.md>), [breach](<https://devfeed.tech/tags/breach.md>), [breaches](<https://devfeed.tech/tags/breaches.md>), [catalog](<https://devfeed.tech/tags/catalog.md>), [channel](<https://devfeed.tech/tags/channel.md>), [cisa](<https://devfeed.tech/tags/cisa.md>), [devops-community](<https://devfeed.tech/tags/devops-community.md>), [layer](<https://devfeed.tech/tags/layer.md>), [observability](<https://devfeed.tech/tags/observability.md>), [orioniq](<https://devfeed.tech/tags/orioniq.md>), [security](<https://devfeed.tech/tags/security.md>), [threat](<https://devfeed.tech/tags/threat.md>), [vulnerabilities](<https://devfeed.tech/tags/vulnerabilities.md>), [vulnerability](<https://devfeed.tech/tags/vulnerability.md>)

### AI overview

Vulnerability Threat Sweep adds a read-only check of live observability data alongside the security team's existing vulnerability process. By default, it runs Mondays at 08:00 and checks vulnerabilities rated 8.5 or higher from the prior 90 days, prioritizing those listed by CISA as exploited. It identifies products and versions in logs, metrics, container images, and scanner alerts; matches affected versions to services; and searches logs and metrics since its previous run for attack signs. Its ranked report gives human-readable actions, flags when data cannot establish a version, and can go to the agent panel, email, Slack, or Microsoft Teams. Teams can change the schedule and severity threshold, add a runbook, and connect OrionIQ integrations. It does not replace scanners or SIEM, and people decide whether to act. The first 10 invocations are free; later runs are billed at the account's price until disabled.

### Source excerpt

TL;DR In most companies, a security team owns vulnerabilities. But in 2026, new vulnerabilities will come out more than twice as fast as in 2025, and attackers will use some of them on the day they come out. Vulnerability Threat Sweep is a new OrionIQ AI agent that adds a second layer of security, from [...]

## Hierarchical Personalized Federated Learning for Fine-Grained Intrusion Detection: A Multi-Class Analysis in Heterogeneous Attack Environments

DevFeed: [Hierarchical Personalized Federated Learning for Fine-Grained Intrusion Detection: A Multi-Class Analysis in Heterogeneous Attack Environments](<https://devfeed.tech/articles/hierarchical-personalized-federated-learning-for-fine-grained-intrusion-detection-a-multi-class-analysis-in-heterogeneous-attack-environments-141478.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.21970>)

Author: Abul Kalam Azad, Travis Atkison

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [NVIDIA Flare](<https://devfeed.tech/topics/nvidia-flare.md>), [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [mlp](<https://devfeed.tech/topics/mlp.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Security](<https://devfeed.tech/topics/security.md>)

Tags: [aggregation](<https://devfeed.tech/tags/aggregation.md>), [attack](<https://devfeed.tech/tags/attack.md>), [classification](<https://devfeed.tech/tags/classification.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [intrusion-detection](<https://devfeed.tech/tags/intrusion-detection.md>), [mlp](<https://devfeed.tech/tags/mlp.md>), [nvidia-flare](<https://devfeed.tech/tags/nvidia-flare.md>), [out-of-distribution-generalization](<https://devfeed.tech/tags/out-of-distribution-generalization.md>), [overhead](<https://devfeed.tech/tags/overhead.md>), [personalization](<https://devfeed.tech/tags/personalization.md>), [privacy](<https://devfeed.tech/tags/privacy.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

The abstract reports that hierarchical personalized federated learning (HPFL), combining multi-tier aggregation with client-level personalization, improved fine-grained intrusion detection on CICIDS2017 using MLP models in NVIDIA FLARE. In the 8-class local evaluation, HPFL reached 0.8324 macro F1, above FedAvg (0.7176) and FedProx (0.5624); its micro F1 was 0.9901. Cross-client 4-class micro F1 was 0.9294, compared with 0.9140 for standalone local models. The study also estimates 194.4 MB transmission overhead for HPFL versus 380.3 MB for conventional FL in the 8-class task. These abstract-level results suggest benefits under heterogeneous attack distributions; they do not establish performance beyond the reported dataset and evaluations.

### Source excerpt

arXiv:2611.21970v1 Announce Type: new Abstract: Intrusion Detection Systems (IDS) play a vital role in protecting modern network infrastructures. Although Federated Learning (FL) enables collaborative training without sharing raw network traffic, global models struggle with non-IID attack distributions. Moreover, practical security operations require fine-grained attack classification for targeted threat responses. To address these challenges, this paper investigates the convergence dynamics and performance of Hierarchical Personalized Federated Learning (HPFL), which combines multi-tier aggregation with client-level personalization, for 8-class, 6-class, and 4-class intrusion detection using Multi-Layer Perceptron (MLP) models implemented in NVIDIA FLARE on the CICIDS2017 dataset. Experimental results show that personalized HPFL models achieve micro F1-scores up to 0.9911 in the 6-class task, while the overall local accuracy reaches 0.9975 in the 8-class task. On 8-class local test sets, HPFL achieves a micro F1-score of 0.9901 and a macro F1-score of 0.8324, outperforming FedAvg (0.7176) and FedProx (0.5624) in macro F1. Cross-client evaluations demonstrate out-of-distribution generalization, with HPFL achieving a 4-class micro F1-score of 0.9294 compared with 0.9140 for standalone local models. Furthermore, distance-weighted network analysis estimates a 48.9% reduction in transmission overhead compared with conventional FL (194.4 MB vs. 380.3 MB for the 8-class task). These findings demonstrate HPFLs potential as an accurate, privacy-preserving, and communication-efficient approach to fine-grained intrusion detection in heterogeneous networks.

## GuardAgent: A Memory-Augmented Agentic Framework for Adaptive Detection of Adversarial Promotions in LLM-Based Recommendation

DevFeed: [GuardAgent: A Memory-Augmented Agentic Framework for Adaptive Detection of Adversarial Promotions in LLM-Based Recommendation](<https://devfeed.tech/articles/guardagent-a-memory-augmented-agentic-framework-for-adaptive-detection-of-adversarial-promotions-in-llm-based-recommendation-141482.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22274>)

Author: Shiyi Yang, Xinshu Li, Chen Wang, Xiwei Xu, Liming Zhu, Lina Yao

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Adversarial attacks](<https://devfeed.tech/topics/adversarial-attacks.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [Machine Intelligence](<https://devfeed.tech/topics/machine-intelligence.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [adversarial](<https://devfeed.tech/tags/adversarial.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [attack](<https://devfeed.tech/tags/attack.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [detection](<https://devfeed.tech/tags/detection.md>), [framework](<https://devfeed.tech/tags/framework.md>), [llm](<https://devfeed.tech/tags/llm.md>), [memory](<https://devfeed.tech/tags/memory.md>), [promotion](<https://devfeed.tech/tags/promotion.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [recommendation](<https://devfeed.tech/tags/recommendation.md>), [recommender-systems](<https://devfeed.tech/tags/recommender-systems.md>), [reflection](<https://devfeed.tech/tags/reflection.md>), [robust](<https://devfeed.tech/tags/robust.md>)

### AI overview

GuardAgent targets promotion-driven attacks on LLM-based recommender systems, where text drives recommendation through semantic understanding and reasoning, creating a harder-to-detect attack surface. The proposed LLM-powered detector loops through Perception, Action, Reflection, and Memory, using continual learning to adapt to unseen threat patterns and producing explainable reasoning traces and outcomes. The abstract reports state-of-the-art generalization in experiments on real-world datasets; it provides no specific metrics or implementation details.

### Source excerpt

arXiv:2611.22274v1 Announce Type: cross Abstract: In traditional recommender systems (RSs), textual information typically serves as auxiliary signals for representation learning. In contrast, in LLM-based RSs, textual information becomes the primary medium for recommendation generation through semantic understanding and reasoning. This shift fundamentally changes the attack surface, making promotion-driven manipulations more feasible, effective, and harder to detect. However, effectively detecting such attacks remains largely unexplored. To fill this gap, we present the first systematic study on detecting promotion-driven attacks against LLM-based RSs, aiming to safeguard next-generation recommendation platforms. Specifically, we propose GuardAgent, a novel LLM-powered agentic detection framework that operates through a loop of Perception, Action, Reflection and Memory. In contrast to conventional LLM-based detectors that function in a static, one-off, and opaque fashion, GuardAgent continually learns and self-evolves to adapt to unseen threat patterns while generating explainable reasoning traces and outcomes. Extensive experiments on real-world datasets demonstrate that GuardAgent achieves state-of-the-art generalization performance, laying the foundation for robust and trustworthy recommendation in practical settings.

## Can You Undo It? Reversibility Classes for AI Agent Actions

DevFeed: [Can You Undo It? Reversibility Classes for AI Agent Actions](<https://devfeed.tech/articles/can-you-undo-it-reversibility-classes-for-ai-agent-actions-139956.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22075>)

Author: Deepak Waghmare, Shaad Sufi

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [MSP MCP](<https://devfeed.tech/topics/msp-mcp.md>)

Tags: [actions](<https://devfeed.tech/tags/actions.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [browser](<https://devfeed.tech/tags/browser.md>), [classes](<https://devfeed.tech/tags/classes.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [databases](<https://devfeed.tech/tags/databases.md>), [file](<https://devfeed.tech/tags/file.md>), [git-merge](<https://devfeed.tech/tags/git-merge.md>), [mcp-servers](<https://devfeed.tech/tags/mcp-servers.md>), [recovery](<https://devfeed.tech/tags/recovery.md>), [reliability](<https://devfeed.tech/tags/reliability.md>), [session](<https://devfeed.tech/tags/session.md>), [tool](<https://devfeed.tech/tags/tool.md>)

### AI overview

The proposed five-level Reversibility Classes vocabulary makes recovery assumptions explicit through argument-sensitive rules, conservative defaults, and a contract to capture prior state. Its registry covers 536 tools across 20 MCP servers. All 738 rule-case checks met declared expectations, but native annotations differed from draft labels for 118 of 481 comparable tools; one AI-assisted reviewer approved 148 ratings, 75 matching the registry, which is not independent agreement. In 2,158 recorded runs, the session guard gated actions in all 29 attributable attack-positive runs, versus 18 for a read/write proxy, while adding nine approval points in 1,209 benign runs. Controlled file, Git, SQLite, and browser experiments found recovery depends on captured state, subsequent changes, editor storage, and recovery route, including a Git merge-state exception. The evidence does not establish registry-wide accuracy, reduced production harm, or general recovery reliability.

### Source excerpt

arXiv:2611.22075v1 Announce Type: new Abstract: Tool-using AI agents change files, databases, access rights and public information, yet permission to call a tool does not establish whether a mistake can be undone. We present Reversibility Classes, a declared five-level vocabulary with argument-sensitive rules, conservative defaults and an explicit prior-state capture contract. The pinned implementation and evidence-linked registry cover 536 tools across 20 MCP servers. All 738 rule-case checks conform to declared expectations, while native annotation mapping differs from draft registry labels for 118 of 481 comparable tools. One AI-assisted reviewer approves 148 ratings, 75 matching the registry; this is not independent agreement. On 2,158 recorded runs, the implemented session guard gates the associated action in all 29 attributable attack-positive runs, compared with 18 for a read/write proxy, while adding nine approval points across 1,209 benign runs. Controlled file, Git, SQLite and three-browser experiments show that recovery depends on captured state, later changes, editor storage and recovery route, and expose a Git merge-state exception. The evidence supports making recovery assumptions explicit and testable. It does not establish registry-wide accuracy, reduced production harm or general recovery reliability.

## IoMT-SecAlarmBench: A Semi-Synthetic Counterfactual Benchmark for Integrity Attacks in IoMT

DevFeed: [IoMT-SecAlarmBench: A Semi-Synthetic Counterfactual Benchmark for Integrity Attacks in IoMT](<https://devfeed.tech/articles/iomt-secalarmbench-a-semi-synthetic-counterfactual-benchmark-for-integrity-attacks-in-iomt-141450.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2608.26416>)

Author: Emmanuel C. Ugwuabonyi, Dmitri Perkins

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [Cybersecurity](<https://devfeed.tech/topics/cybersecurity.md>), [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>)

Tags: [attacks](<https://devfeed.tech/tags/attacks.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [detection](<https://devfeed.tech/tags/detection.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [integrity](<https://devfeed.tech/tags/integrity.md>), [iomt](<https://devfeed.tech/tags/iomt.md>), [semi](<https://devfeed.tech/tags/semi.md>), [synthetic](<https://devfeed.tech/tags/synthetic.md>)

### AI overview

IoMT-SecAlarmBench injects controlled integrity attacks into genuine coupled ECG+PPG recordings, preserving each window's attack cause and the clean signal that would have appeared without it. Its design covers four attack morphologies, four severity levels, two physiological plausibility conditions, and replay attacks. Across six detectors from five method families, replay attacks and low-amplitude transient spikes remain close to chance-level detection. The strongest detector on hard cases flags sensor fault or artifact windows at 5.3 times its false-alarm rate on normal data, exposing a trade-off between attack detection and distinguishing attacks from faults. Three-way classification performs poorly on genuine physiological events; a leakage audit also suggests identifying information partly explains previously reported performance on a dual-modality network dataset. The authors release the benchmark and associated generation and evaluation resources.

### Source excerpt

arXiv:2608.26416v2 Announce Type: replace Abstract: The Internet of Medical Things (IoMT) combines clinical physiological data with cyber-system information, creating challenges in determining whether an abnormal reading reflects a genuine physiological event, a device fault, or a cyber-attack within the expected physiological range. Answering this requires counterfactual ground truth, which no existing dataset provides. We present IoMT-SecAlarmBench, a semi-synthetic benchmark that injects controlled integrity attacks into genuine coupled ECG+PPG recordings using a structured experimental design combining four attack morphologies, four severity levels, two physiological plausibility conditions, and replay attacks. Each injected window retains its cause, attack subtype, and the clean signal that would have been observed without the attack. We evaluate six detectors from five method families using threshold-independent measures and a matched false-alarm budget. Results show no method consistently detects the most difficult cases: replay attacks and low-amplitude transient spikes remain close to chance-level performance across detectors. Results also reveal a trade-off between detecting attacks and distinguishing them from sensor faults: the best-performing detector on hard cases flags fault/artifact windows at 5.3 times its false-alarm rate on normal data. Three-way classification performs poorly for genuine physiological events, and a leakage audit of a dual-modality network dataset indicates previously reported IoMT intrusion-detection performance is partly driven by identifying information. Benchmark, generation code, preprocessing, evaluation tools, and datasheet are released.

## How we're using AI to make Next.js more secure

DevFeed: [How we're using AI to make Next.js more secure](<https://devfeed.tech/articles/how-we-re-using-ai-to-make-next-js-more-secure-138312.md>)

Original publisher: [Read original article](<https://nextjs.org/blog/how-were-using-ai-to-make-nextjs-more-secure>)

Published: 2026-11-17T19:38:31.791422Z

Content type: article

Language: en

Sources: [Next.js](<https://devfeed.tech/sources/next-js-blog.md>)

Topics: [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [Tool](<https://devfeed.tech/topics/tool.md>), [alert triage](<https://devfeed.tech/topics/alert-triage.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [qualitygates](<https://devfeed.tech/topics/qualitygates.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [upgrade](<https://devfeed.tech/topics/upgrade.md>), [Legacy Modernization](<https://devfeed.tech/topics/legacy-modernization.md>)

Tags: [adapters](<https://devfeed.tech/tags/adapters.md>), [ai](<https://devfeed.tech/tags/ai.md>), [audit](<https://devfeed.tech/tags/audit.md>), [backlog](<https://devfeed.tech/tags/backlog.md>), [bot](<https://devfeed.tech/tags/bot.md>), [bounty](<https://devfeed.tech/tags/bounty.md>), [bug-bounty](<https://devfeed.tech/tags/bug-bounty.md>), [bug-bounty-program](<https://devfeed.tech/tags/bug-bounty-program.md>), [bugs](<https://devfeed.tech/tags/bugs.md>), [build](<https://devfeed.tech/tags/build.md>), [bypass](<https://devfeed.tech/tags/bypass.md>), [canary](<https://devfeed.tech/tags/canary.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [case](<https://devfeed.tech/tags/case.md>), [ci](<https://devfeed.tech/tags/ci.md>), [cloud-provider](<https://devfeed.tech/tags/cloud-provider.md>), [compatibility](<https://devfeed.tech/tags/compatibility.md>), [next-js](<https://devfeed.tech/tags/next-js.md>), [security](<https://devfeed.tech/tags/security.md>), [security-advisories](<https://devfeed.tech/tags/security-advisories.md>)

### AI overview

Next.js reports more security advisories as AI makes older, previously impractical bugs easier to find; of 51 vulnerabilities found in 2026, 70% were in code at least a year old, and many serious issues were in dependencies. The team describes a bug bounty, an internal Eve-powered bot for finding and triaging reports, a Trail of Bits audit, monthly scheduled security releases, and Vercel Agent security reviews on every pull request. It is also formalizing how hosting layers serve apps through Adapters and reviewing dependency risks. Starting in Next.js 16.4, `next dev` and `next build` warn about known vulnerabilities. DevTools provides a Vulnerability Insight, while `npx next@canary upgrade --agent` selects the latest safe release within the oldest major version with a fix and delegates migration to a coding agent.

### Source excerpt

Why you're seeing more Next.js security advisories, and what we're doing about it.

## Securing Your Agents: A Hands-On Guide to Agent Anomaly Detection

DevFeed: [Securing Your Agents: A Hands-On Guide to Agent Anomaly Detection](<https://devfeed.tech/articles/securing-your-agents-a-hands-on-guide-to-agent-anomaly-detection-136557.md>)

Original publisher: [Read original article](<https://developers.googleblog.com/securing-your-agents-a-hands-on-guide-to-agent-anomaly-detection/>)

Author: Achuth Narayan Rajagopal; Derek Luan

Published: 2026-11-17T05:43:32.994674Z

Content type: tutorial

Language: en

Sources: [Google Developers Blog](<https://devfeed.tech/sources/google-developers-blog.md>)

Topics: [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [Cloud Monitoring](<https://devfeed.tech/topics/cloud-monitoring.md>), [ai observability](<https://devfeed.tech/topics/ai-observability.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Detection engineering](<https://devfeed.tech/topics/detection-engineering.md>), [alert triage](<https://devfeed.tech/topics/alert-triage.md>), [google-adk](<https://devfeed.tech/topics/google-adk.md>), [AI for customer service automation](<https://devfeed.tech/topics/ai-for-customer-service-automation.md>)

Tags: [adk](<https://devfeed.tech/tags/adk.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [alerts](<https://devfeed.tech/tags/alerts.md>), [anomaly-detection](<https://devfeed.tech/tags/anomaly-detection.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cloud-monitoring](<https://devfeed.tech/tags/cloud-monitoring.md>), [configure](<https://devfeed.tech/tags/configure.md>), [customer](<https://devfeed.tech/tags/customer.md>), [customer-support](<https://devfeed.tech/tags/customer-support.md>), [deploy](<https://devfeed.tech/tags/deploy.md>), [detection](<https://devfeed.tech/tags/detection.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [guide](<https://devfeed.tech/tags/guide.md>), [monitor](<https://devfeed.tech/tags/monitor.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>), [platform](<https://devfeed.tech/tags/platform.md>), [sample](<https://devfeed.tech/tags/sample.md>), [security](<https://devfeed.tech/tags/security.md>), [telemetry](<https://devfeed.tech/tags/telemetry.md>)

### AI overview

Agent Anomaly Detection on the Gemini Platform analyzes agent traces and logs to flag sessions that stray beyond an agent's intended job. The guide demonstrates it with a deliberately over-permissive customer support agent using canned in-memory data: after telemetry and message logging are enabled, a normal session and a simulated payroll-data request are processed, and the latter is flagged for tool misuse. Setup requires a Cloud Logging bucket and Observability dataset in the same US or EU multi-region; monitored sessions are analyzed after setup, which takes about 30 minutes, and new sessions are scanned within about five minutes. The example finding was High severity with 95% probability, but detector results and severities can vary because the analysis models are non-deterministic. Cloud Monitoring metrics support anomaly and coverage alerts; Security Command Center can receive anomaly findings when enabled for the organization. The excerpt cautions against copying the intentionally unsafe demo tool into production.

### Source excerpt

This guide walks developers through setting up Agent Anomaly Detection on the Gemini Enterprise Agent Platform to monitor AI agent telemetry and catch behavioral risks. It demonstrates how to deploy a sample customer support agent, trigger out-of-scope security findings, and configure proactive alerts using Cloud Monitoring and Security Command Center.

## Experience: ENTRAP - An IaC Enterprise Cyber Range for Reproducible Security Assessment and Dataset Generation

DevFeed: [Experience: ENTRAP - An IaC Enterprise Cyber Range for Reproducible Security Assessment and Dataset Generation](<https://devfeed.tech/articles/experience-entrap-an-iac-enterprise-cyber-range-for-reproducible-security-assessment-and-dataset-generation-139307.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.20594>)

Author: Rathan Appana, Aditya Kulkarni, Bheemarjuna Reddy Tamma

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [Security](<https://devfeed.tech/topics/security.md>), [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [Threat monitoring](<https://devfeed.tech/topics/threat-monitoring.md>), [cyber resiliency](<https://devfeed.tech/topics/cyber-resiliency.md>)

Tags: [ansible](<https://devfeed.tech/tags/ansible.md>), [assessment](<https://devfeed.tech/tags/assessment.md>), [attack](<https://devfeed.tech/tags/attack.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [automation](<https://devfeed.tech/tags/automation.md>), [backup](<https://devfeed.tech/tags/backup.md>), [backups](<https://devfeed.tech/tags/backups.md>), [breach](<https://devfeed.tech/tags/breach.md>), [campaign](<https://devfeed.tech/tags/campaign.md>), [classifier](<https://devfeed.tech/tags/classifier.md>), [clients](<https://devfeed.tech/tags/clients.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cyber](<https://devfeed.tech/tags/cyber.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [experience](<https://devfeed.tech/tags/experience.md>), [generation](<https://devfeed.tech/tags/generation.md>), [iac](<https://devfeed.tech/tags/iac.md>), [range](<https://devfeed.tech/tags/range.md>), [security](<https://devfeed.tech/tags/security.md>), [security-assessment](<https://devfeed.tech/tags/security-assessment.md>)

### AI overview

ENTRAP is an Infrastructure-as-Code cyber range for repeatable post-compromise security experiments. It uses Ansible, KVM/Libvirt, and Cloud-init to provision and reset a segmented enterprise network with services including a gateway, DMZ, DNS, DHCP, backup and web servers, and client machines. The authors run three scenarios from clean states: ransomware, Layer-2 DHCP starvation with rogue DHCP, and perimeter web exploitation. ENTRAP also generates labeled attack datasets; the authors use collected data to train and evaluate a Random Forest for ransomware detection. The abstract says the codebase, logs, and datasets are publicly released, but provides no classifier results or detailed deployment requirements.

### Source excerpt

arXiv:2611.20594v1 Announce Type: new Abstract: An enterprise breach causes most of its damage after the perimeter is crossed. Once an attacker gains a foothold, they can move laterally to other hosts, take over the trusted services of the network, and encrypt the backups needed for recovery. Defenders, on the other hand, need to study this post-compromise stage, but they cannot rehearse it on a production enterprise network. Building such an enterprise network manually is time-consuming, and resetting it to its clean state between runs is still harder. As a result, security experiments are difficult to perform, compare and reproduce. We develop Enterprise Network Testbed for Reproducible Attack and Defense Practices (ENTRAP), an Infrastructure-as-Code (IaC) cyber range that defines a fully segmented enterprise as version-controlled automation. ENTRAP uses Ansible, KVM/Libvirt, and Cloud-init to provision the environment and reset it to a clean state whenever necessary. The enterprise network includes several entities such as a gateway, an internal Demilitarized Zone (DMZ), DNS, DHCP, a backup server, a web server, and clients. On this network, a user can learn to assemble the entities, launch attacks, and write rules or defensive measures that harden its security. We launch three attacks: a Ransomware-as-a-Service (RaaS)-backed ransomware campaign, a Layer-2 DHCP starvation and rogue DHCP attack, and perimeter web exploitation. Each attack runs from a clean state, and ENTRAP acts as a reproducible generator of labeled attack datasets. Using the collected dataset, we train a Random Forest classifier for ransomware detection and present its evaluation results. We publicly release the codebase, collected logs, and datasets to facilitate further research.

## TRACE: Topological Representations for Anomaly detection through Contrastive Embeddings

DevFeed: [TRACE: Topological Representations for Anomaly detection through Contrastive Embeddings](<https://devfeed.tech/articles/trace-topological-representations-for-anomaly-detection-through-contrastive-embeddings-137716.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.21548>)

Author: Sydney Johns

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [Representation learning](<https://devfeed.tech/topics/representation-learning.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [metric learning](<https://devfeed.tech/topics/metric-learning.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [graph theory](<https://devfeed.tech/topics/graph-theory.md>)

Tags: [anomaly-detection](<https://devfeed.tech/tags/anomaly-detection.md>), [attack](<https://devfeed.tech/tags/attack.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [contrastive-learning](<https://devfeed.tech/tags/contrastive-learning.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [detection](<https://devfeed.tech/tags/detection.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [framework](<https://devfeed.tech/tags/framework.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graphs](<https://devfeed.tech/tags/graphs.md>), [intrusion-detection](<https://devfeed.tech/tags/intrusion-detection.md>), [malicious](<https://devfeed.tech/tags/malicious.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [representation-learning](<https://devfeed.tech/tags/representation-learning.md>), [topology](<https://devfeed.tech/tags/topology.md>), [trace](<https://devfeed.tech/tags/trace.md>), [validation](<https://devfeed.tech/tags/validation.md>)

### AI overview

TRACE learns representations from benign system-activity graphs by combining message passing with topological features, then scores anomalies in the contrastive embedding space. Attack labels are not used for representation learning; a labeled benign-and-malicious validation set is used to calibrate the anomaly threshold. On StreamSpot, GraSec-IoT, and Unicorn Wget, TRACE reports F1 scores of 0.923, 0.790, and 0.583. It exceeds benign-only GraphCL on StreamSpot and Unicorn Wget but trails it on GraSec-IoT. A supervised graph neural network performs best on the first two datasets, while TRACE leads on Unicorn Wget, so its advantage varies by graph setting.

### Source excerpt

arXiv:2611.21548v1 Announce Type: cross Abstract: Intrusion detectors must recognize evolving malicious behavior even when confirmed attack labels are scarce or incomplete. We present TRACE, a topology-aware graph contrastive learning framework for label-efficient intrusion detection. TRACE learns from benign system-activity graphs by combining message-passing and topological representations, then assigns anomaly scores in the same projected embedding space optimized by the contrastive objective. This design captures both local interactions and graph-scale structural deviations without using attack labels during representation learning. A labeled validation set containing benign and malicious graphs is used only to calibrate the anomaly threshold. We evaluate TRACE on StreamSpot, GraSec-IoT, and Unicorn Wget against a supervised graph neural network and the benign-only GraphCL baseline. TRACE obtains F1 scores of 0.923, 0.790, and 0.583, respectively. Compared with GraphCL, this is higher on StreamSpot (0.450) and Unicorn Wget (0.203), but lower on GraSec-IoT (0.975). The supervised model leads on StreamSpot and GraSec-IoT, whereas TRACE has the highest F1 on Unicorn Wget. The mixed results show that topology-aware benign-only learning can improve detection in some graph settings but does not provide a uniform advantage.

## Google found hackers using autonomous AI agents to turn security patches into exploits

DevFeed: [Google found hackers using autonomous AI agents to turn security patches into exploits](<https://devfeed.tech/articles/google-found-hackers-using-autonomous-ai-agents-to-turn-security-patches-into-exploits-136354.md>)

Original publisher: [Read original article](<https://thenewstack.io/autonomous-ai-exploit-agents/>)

Author: Amanda Caswell

Published: 2026-11-16T21:27:38Z

Content type: news

Language: en

Sources: [The New Stack](<https://devfeed.tech/sources/the-new-stack.md>)

Topics: [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Security](<https://devfeed.tech/topics/security.md>), [patches](<https://devfeed.tech/topics/patches.md>), [Reverse Engineering](<https://devfeed.tech/topics/reverse-engineering.md>), [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [Security, Privacy and Abuse Prevention](<https://devfeed.tech/topics/security-privacy-and-abuse-prevention.md>)

Tags: [access-controls](<https://devfeed.tech/tags/access-controls.md>), [agent-harnesses](<https://devfeed.tech/tags/agent-harnesses.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [application-security](<https://devfeed.tech/tags/application-security.md>), [autonomous-ai-agents](<https://devfeed.tech/tags/autonomous-ai-agents.md>), [cairn](<https://devfeed.tech/tags/cairn.md>), [cve-2026-109618](<https://devfeed.tech/tags/cve-2026-109618.md>), [cve-2026-109619](<https://devfeed.tech/tags/cve-2026-109619.md>), [cyberstrikeai](<https://devfeed.tech/tags/cyberstrikeai.md>), [exploit](<https://devfeed.tech/tags/exploit.md>), [exploit-agent](<https://devfeed.tech/tags/exploit-agent.md>), [exploitation](<https://devfeed.tech/tags/exploitation.md>), [exploits](<https://devfeed.tech/tags/exploits.md>), [google](<https://devfeed.tech/tags/google.md>), [hackers](<https://devfeed.tech/tags/hackers.md>), [model-context-protocol-mcp](<https://devfeed.tech/tags/model-context-protocol-mcp.md>), [patches](<https://devfeed.tech/tags/patches.md>), [security](<https://devfeed.tech/tags/security.md>), [security-patches](<https://devfeed.tech/tags/security-patches.md>)

### AI overview

Google and Mandiant report attackers using multi-agent LLM frameworks to automate patch diffing, generate exploit candidates, and try them against targets. In one case, a publicly exposed server ran `exploit_agent`, which connected frontier and locally hosted models; researchers could not identify which models performed which tasks or determine whether the framework obtained the stolen data found on the server. Google also observed CAIRN in intrusions targeting U.S. aerospace organizations, while CyberStrikeAI and HexStrike AI are described as other approaches with different orchestration and tool setups. The excerpt cites rapid LLM-assisted exploit development after vulnerability disclosures as a challenge for defenders, but says the observed frameworks produce detectable network traffic and artifacts, and their hallucinations can derail attacks or expose operators. The excerpt does not establish how often generated exploits succeed.

### Source excerpt

Google's Threat Intelligence Group says attackers are using autonomous AI agents to reverse-engineer security patches, generate exploits, and attempt to The post Google found hackers using autonomous AI agents to turn security patches into exploits appeared first on The New Stack.

## New Huntress Security Insights Report & Reporting Center

DevFeed: [New Huntress Security Insights Report & Reporting Center](<https://devfeed.tech/articles/new-huntress-security-insights-report-reporting-center-136865.md>)

Original publisher: [Read original article](<https://www.huntress.com/blog/security-insights-report>)

Author: Mandy Ruggiero

Published: 2026-11-16T15:00:00Z

Content type: release

Language: en

Sources: [Huntress Blog](<https://devfeed.tech/sources/huntress-blog.md>)

Topics: [Security](<https://devfeed.tech/topics/security.md>), [Security Operations Center](<https://devfeed.tech/topics/security-operations-center.md>), [Threat monitoring](<https://devfeed.tech/topics/threat-monitoring.md>), [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [Endpoint security](<https://devfeed.tech/topics/endpoint-security.md>), [Managed Services](<https://devfeed.tech/topics/managed-services.md>), [Security Information and Event Management (SIEM)](<https://devfeed.tech/topics/siem-security.md>)

Tags: [about](<https://devfeed.tech/tags/about.md>), [account](<https://devfeed.tech/tags/account.md>), [addition](<https://devfeed.tech/tags/addition.md>), [advanced](<https://devfeed.tech/tags/advanced.md>), [all](<https://devfeed.tech/tags/all.md>), [analyst](<https://devfeed.tech/tags/analyst.md>), [announcement](<https://devfeed.tech/tags/announcement.md>), [attack](<https://devfeed.tech/tags/attack.md>), [huntress](<https://devfeed.tech/tags/huntress.md>), [insights](<https://devfeed.tech/tags/insights.md>), [one](<https://devfeed.tech/tags/one.md>), [one-page-summary](<https://devfeed.tech/tags/one-page-summary.md>), [report](<https://devfeed.tech/tags/report.md>), [reporting](<https://devfeed.tech/tags/reporting.md>), [security](<https://devfeed.tech/tags/security.md>), [security-insights](<https://devfeed.tech/tags/security-insights.md>), [summary](<https://devfeed.tech/tags/summary.md>), [threat](<https://devfeed.tech/tags/threat.md>), [threat-report](<https://devfeed.tech/tags/threat-report.md>), [updated](<https://devfeed.tech/tags/updated.md>)

### AI overview

Huntress is rolling out redesigned monthly and quarterly Security Insights Reports, renamed from Threat Reports, to show security posture and outcomes across Managed EDR, ITDR, SIEM, and ISPM. The report adds an executive summary with a protection funnel, SOC notes, and incident trends; firewall status and external attack-surface pages; and a cross-product incident summary. A separate one-page report gives nontechnical stakeholders a plain-language view of protection and investigations; it is emailed monthly and available in the portal. Both the new and legacy reports will be provided for a few months during transition. The Investigations View supplies a chronological timeline that includes benign closures. Planned additions include account-level reports, more Reporting Center customization, and a dedicated ISPM compliance report.

### Source excerpt

Meet the redesigned Huntress Security Insights Report (formerly known as Threat Report), a one-page summary in an updated reporting center.

## Prevention Under Pressure: Why most AI governance is "detection wearing prevention clothes"

DevFeed: [Prevention Under Pressure: Why most AI governance is "detection wearing prevention clothes"](<https://devfeed.tech/articles/prevention-under-pressure-why-most-ai-governance-is-detection-wearing-prevention-clothes-137191.md>)

Original publisher: [Read original article](<https://www.chainguard.dev/unchained/prevention-under-pressure-why-most-ai-governance-is-detection-wearing-prevention-clothes>)

Published: 2026-11-16T00:00:00Z

Content type: article

Language: en

Sources: [Chainguard: Unchained](<https://devfeed.tech/sources/chainguard-unchained.md>)

Topics: [ai-governance](<https://devfeed.tech/topics/ai-governance.md>), [shadow AI](<https://devfeed.tech/topics/shadow-ai.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [Incident response](<https://devfeed.tech/topics/incident-response.md>)

Tags: [about](<https://devfeed.tech/tags/about.md>), [access-management](<https://devfeed.tech/tags/access-management.md>), [adopting](<https://devfeed.tech/tags/adopting.md>), [advice](<https://devfeed.tech/tags/advice.md>), [after](<https://devfeed.tech/tags/after.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-driven-attacks](<https://devfeed.tech/tags/ai-driven-attacks.md>), [ai-governance](<https://devfeed.tech/tags/ai-governance.md>), [chainguard](<https://devfeed.tech/tags/chainguard.md>), [ciso](<https://devfeed.tech/tags/ciso.md>), [clothes](<https://devfeed.tech/tags/clothes.md>), [detection](<https://devfeed.tech/tags/detection.md>), [governance](<https://devfeed.tech/tags/governance.md>), [security](<https://devfeed.tech/tags/security.md>), [shift](<https://devfeed.tech/tags/shift.md>), [threats](<https://devfeed.tech/tags/threats.md>), [under](<https://devfeed.tech/tags/under.md>)

### AI overview

Kayla Williams argues that many AI governance programs monitor tool use after the fact instead of deciding what is allowed beforehand. Her TIDE model--Tier, Intake, Determine controls, Enact decision--automatically approves low-risk uses within the company's risk appetite and subjects high-risk uses, typically involving sensitive data, to scrutiny. She says data classification should cover proprietary models and formulas as well as PII, and identity and access management is essential. Williams also warns about abandoned agents built for critical processes, and recommends auditing existing tools before buying new ones. On incident response, she contrasts detection-led investigations with prevention built into software at the source, which can reduce the blast radius if a vulnerable component is absent or never exploited. The excerpt also describes AI-generated phishing and a deepfake CEO as threats that challenged her assumptions.

### Source excerpt

CISO Kayla Williams joins Chainguard's Prevention Under Pressure to discuss AI threats, security governance, and the shift from detection to prevention.

## Identifying FortiGate Firmware From a Single ClientHello

DevFeed: [Identifying FortiGate Firmware From a Single ClientHello](<https://devfeed.tech/articles/identifying-fortigate-firmware-from-a-single-clienthello-135997.md>)

Original publisher: [Read original article](<https://www.vulncheck.com/blog/fortigate-firmware-clienthello>)

Author: Adam Powis

Published: 2026-11-16T00:00:00Z

Content type: news

Language: en

Sources: [VulnCheck](<https://devfeed.tech/sources/vulncheck.md>)

Topics: [Fortigate](<https://devfeed.tech/topics/fortigate.md>), [Exposure Management](<https://devfeed.tech/topics/exposure-management.md>), [TLS (Transport Layer Security)](<https://devfeed.tech/topics/tls.md>), [cve remediation](<https://devfeed.tech/topics/cve-remediation.md>), [threat detection](<https://devfeed.tech/topics/threat-detection.md>)

Tags: [cve](<https://devfeed.tech/tags/cve.md>), [fingerprint](<https://devfeed.tech/tags/fingerprint.md>), [firmware](<https://devfeed.tech/tags/firmware.md>), [fortigate](<https://devfeed.tech/tags/fortigate.md>), [fortios](<https://devfeed.tech/tags/fortios.md>), [generation](<https://devfeed.tech/tags/generation.md>), [internet](<https://devfeed.tech/tags/internet.md>), [management](<https://devfeed.tech/tags/management.md>), [port](<https://devfeed.tech/tags/port.md>), [range](<https://devfeed.tech/tags/range.md>), [tls](<https://devfeed.tech/tags/tls.md>), [version](<https://devfeed.tech/tags/version.md>)

### AI overview

The study found 375,904 internet-facing FortiGate hosts exposing FGFM on port 541; Fortinet says this management port should not be internet-accessible. Although only 269 of 838,100 hosts identified as FortiOS advertised a version, a TLS ClientHello sent by each exposed host can be fingerprinted with JA4 and mapped to one of six generations and a range of FortiOS versions. Comparing those ranges with vulnerability data, the researchers estimate that 160,171 hosts (42.6%) are in generations where every measured version has a known-exploited CVE. This is a generation-level exposure estimate, not a verdict on each host's exact version; some generations combine supported and end-of-life branches, and unmeasured versions and older CVE ranges limit the counts. The researchers recommend restricting FGFM on ports 541 and 542 to management networks or required peer addresses. They also provide Suricata and Snort rules because those tools do not recognize this listener-sent ClientHello through their usual TLS or JA4 parsing.

### Source excerpt

About 376,000 internet-facing FortiGate hosts expose their FGFM management port and answer a connection with a TLS ClientHello. A JA4 fingerprint of that ClientHello places each host in a FortiOS generation, which maps to a range of versions and the CVEs that affect them. 160,171 hosts (42.6%) are in generations where every version we measured has a known-exploited CVE.

[Next page](<https://devfeed.tech/topics/threat-detection.md?cursor=WyIyMDI2LTExLTE2VDAwOjAwOjAwKzAwOjAwIiwgIjkxMGZjYTU5LTZkMWItNDc1OC1hYjNhLTU0MTcyMzI5ODExMSJd>)