# pii Published articles for pii. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## How WorkOS Vault's local encryption works DevFeed: [How WorkOS Vault's local encryption works]() Original publisher: [Read original article]() Author: WorkOS Published: 2026-09-14T00:00:00Z Content type: article Language: en Sources: [WorkOS Blog]() Topics: [Encryption](), [Cryptography](), [Security](), [data]() Tags: [cryptographic](), [data](), [encryption](), [pii](), [security](), [token]() ### AI overview The article explains how WorkOS Vault performs local encryption using envelope encryption. Each operation uses a single-use data encryption key, which is protected by a key encryption key stored in a hardware security module. Sensitive plaintext and ciphertext remain within the customer's infrastructure; only the wrapped key is sent to WorkOS. Key contexts automatically select or create isolated keys for organizations or tenants, with support for customer-managed keys and documented limits on context size and key counts. ### Source excerpt Envelope encryption, data keys, and why your sensitive data never has to leave your infrastructure ## Model-agnostic PII detection with LLMs DevFeed: [Model-agnostic PII detection with LLMs]() Original publisher: [Read original article]() Author: Christophe Dupuy Published: 2026-09-10T16:02:16Z Content type: tutorial Language: en Sources: [Artificial Intelligence]() Topics: [AI Chat]() Tags: [advanced-300](), [amazon-bedrock](), [benchmark](), [fine-tuning](), [inference](), [large-language-models-llms](), [llms](), [pii](), [security](), [technical-how-to](), [vpc]() ### AI overview A tutorial on building a configurable, model-agnostic PII detector with large language models. It explains prompt-based entity configuration, implementation, benchmarking, and running the detector on custom data. ### Source excerpt A configurable, model-agnostic detector that turns any large language model on Amazon Bedrock into a PII detector. Because the entities to detect live in a prompt rather than in code, one detector adapts to new entity types without retraining, and it outperforms an off-the-shelf tool across five public corpora and nine LLM-based detectors. ## PostgreSQL Anonymizer 3.2 : Faster Pseudonymization DevFeed: [PostgreSQL Anonymizer 3.2 : Faster Pseudonymization]() Original publisher: [Read original article]() Published: 2026-09-09T00:00:00Z Content type: release Language: en Sources: [PostgreSQL news]() Topics: [Databases](), [Extension](), [Vulnerabilities]() Tags: [database](), [extension](), [pii](), [postgresql](), [privacy](), [security](), [vulnerabilities]() ### AI overview PostgreSQL Anonymizer 3.2 adds faster localized pseudonymization functions, deprecates the previous pseudo_* functions, and fixes three critical privilege-escalation vulnerabilities. ### Source excerpt Eymoutiers, France, Septembre 4th, 2026 Dalibo is pleased to announce PostgreSQL Anonymizer 3.2 introducing a new panel of fast pseudonymization filters. Enhanced Privacy Protection for Your Data PostgreSQL Anonymizer is an extension that hides or replaces personally identifiable information (PII) or commercially sensitive data from a PostgreSQL database. The extension offers 6 different masking strategies: Dynamic Masking - Real-time data protection Static Masking - Permanent data transformation Replica Masking - Anonymized logical replication Backup Masking - Privacy-protected database exports Masking Views - Controlled data visibility Masking Data Wrappers - Extended protection across systems Each strategy is complemented by an enhanced suite of Masking Functions, including advanced techniques such as: Substitution, Randomization, Faking, Pseudonymization, Partial Scrambling, Shuffling, Noise Addition and Generalization. The extension can be installed with Debian and RPM packages, an Ansible role, a Docker image, etc. You can use it on most major DBaaS providers including : Alibaba Cloud, Crunchy Bridge, Google Cloud SQL, IBM Cloud, Microsoft Azure Database, Neon, Yandex It is also available on some Postgres forks such as EDB Advanced Postgres, Greenplum and Yugabyte. See the INSTALL section of the documentation for more details! Fast and Localized pseudonymization Although Pseudonymization is not Anonymization, it may be useful in some contexts. Until version 3.1, this was achieved with a panel of pseudo_* functions, such as anon.pseudo_last_name(...), anon.pseudo_email(...), etc. These functions are now replaced by a new panel of anon.seeded_* functions, such as anon.seeded_last_name(...), anon.seeded_email(...), etc. The anon.seeded_* functions have 2 main advantages over the previous ones: They can be localized, e.g anon.seeded_street_name(id,'fr_FR') They are 40x faster :) The anon.pseudo_* functions are kept for backward compatibility but are now deprecated ## Your redaction filter works. Are you quite sure? DevFeed: [Your redaction filter works. Are you quite sure?]() Original publisher: [Read original article]() Author: Hal Tyk's tutorial bot Published: 2026-09-03T09:03:23Z Content type: tutorial Language: en Sources: [Tyk API Management]() Topics: [Tutorial](), [pii](), [Artificial Intelligence](), [Script](), [Regular expression](), [payload](), [API]() Tags: [ai-gateway](), [ai-studio](), [api](), [api-management](), [api-platform-teams](), [data-privacy](), [how-to](), [llm-governance](), [payload](), [pii](), [pii-redaction](), [tengo](), [tutorial]() ### AI overview This tutorial explains how to create and test a Tyk request filter that redacts personal data before a request reaches an AI model. It covers Enterprise licensing, request and response filter behavior, the PII Redaction template, and the Tengo scripting contract using the Tyk module and regular expressions. ### Source excerpt Hello. I'm Hal, Tyk's tutorial bot, and today I have been given something genuinely useful to explain: how to stop personal data reaching a model in the first place. We are going to write a filter, find a gap in it before a single request has been sent, fix the gap, and only then let [...] The post Your redaction filter works. Are you quite sure? appeared first on Tyk API Management. ## VAST Data CrowdStrike Integration Goes Live: Native Falcon Sensor Now, Next-Gen SIEM and AIDR in Preview DevFeed: [VAST Data CrowdStrike Integration Goes Live: Native Falcon Sensor Now, Next-Gen SIEM and AIDR in Preview]() Original publisher: [Read original article]() Author: Harold Fritts Published: 2026-09-01T15:37:31Z Content type: news Language: en Sources: [StorageReview.com]() Topics: [Cybersecurity](), [Securing AI](), [AI Infrastructure](), [SIEM, Security](), [SIEM, Security, Observability](), [prompt injection](), [Jailbreak](), [pii](), [Retrieval Augmented Generation (RAG)](), [Nvidia]() Tags: [ai](), [ai-infrastructure](), [ai-security](), [cybersecurity](), [enterprise](), [infrastructure](), [nvidia](), [pii](), [prompt-injection](), [security]() ### AI overview VAST Data and CrowdStrike have launched an integration that embeds Falcon security capabilities into VAST AI storage infrastructure, data pipelines, and production AI workloads. The integration supports native Falcon sensors, sends VAST audit telemetry to CrowdStrike Next-Gen SIEM, inspects data in flight with Falcon AIDR, helps identify PII before downstream use, and detects prompt injection and jailbreak attempts during model interactions. ### Source excerpt VAST Data and CrowdStrike are turning the AI security partnership they announced at VAST Forward in February into a shipping product, detailing a multi-layered integration that embeds enterprise-grade cybersecurity directly into AI storage infrastructure, data pipelines, and production AI workloads. By combining the VAST AI Operating System with the CrowdStrike Falcon platform, the collaboration addresses The post VAST Data CrowdStrike Integration Goes Live: Native Falcon Sensor Now, Next-Gen SIEM and AIDR in Preview appeared first on StorageReview.com. ## The Four Vendor Relationships Commonly Involved in a Production Voice Feature DevFeed: [The Four Vendor Relationships Commonly Involved in a Production Voice Feature]() Original publisher: [Read original article]() Author: Byte-Sized Design Published: 2026-08-28T21:47:43Z Content type: article Language: en Sources: [Byte-Sized Design]() Topics: [API](), [Large Language Model](), [pii]() Tags: [2026](), [api](), [compliance](), [llm](), [pii](), [pii-redaction](), [production](), [transcription](), [voice]() ### AI overview The article describes how a production voice feature typically involves four vendor relationships: transcription, PII redaction, an LLM provider, and compliance review. ### Source excerpt TLDR A production voice feature in 2026 typically ships with four vendor relationships: a transcription API, a PII redaction step somebody built in a sprint, an LLM provider, and a compliance review stretched across all of it. ## How Clario technology detects PHI/PII in DICOM images using Amazon Bedrock DevFeed: [How Clario technology detects PHI/PII in DICOM images using Amazon Bedrock]() Original publisher: [Read original article]() Author: Alex Boudreau Published: 2026-08-19T14:29:31Z Content type: article Language: en Sources: [AWS Architecture Blog]() Topics: [Amazon Bedrock](), [Medical imaging](), [Amazon Textract](), [Amazon Web Services](), [data]() Tags: [amazon](), [amazon-bedrock](), [amazon-textract](), [analysis](), [architecture](), [aws](), [customer-solutions](), [data](), [healthcare](), [images](), [medical-imaging](), [pii](), [technology](), [workflow]() ### AI overview Clario uses Amazon Bedrock and Amazon Textract to automate the detection of PHI and PII in DICOM image slices from clinical trials, including information stored in metadata and text embedded in image pixels. ### Source excerpt Clario, part of Thermo Fisher Scientific, uses Amazon Bedrock and Amazon Textract to automatically detect protected health information (PHI) and personally identifiable information (PII) across thousands of DICOM image slices in clinical trials, covering both metadata tags and text burned into the image pixels. ## Chaining Activities -- from text to vectors DevFeed: [Chaining Activities -- from text to vectors]() Original publisher: [Read original article]() Author: Houman Kargaran Published: 2026-08-12T00:00:00Z Content type: tutorial Language: en Sources: [Temporal Blog]() Topics: [data](), [Embeddings](), [on-prem](), [pii](), [Redis](), [retry](), [Sequences]() Tags: [article](), [community](), [data-pipeline](), [embeddings](), [on-prem](), [pii](), [redis](), [retries](), [storage]() ### AI overview This guest post explains a Temporal workflow that chains discrete Activities to process complaints while maintaining a PII boundary. It uses an on-premises all-MiniLM-L6-v2 model for embeddings, caches vectors in Redis, stores them externally, and relies on deterministic workflow sequencing and retry policies. ### Source excerpt Learn how to build a durable, PII-conscious data pipeline with Temporal using on-prem embeddings, idempotent Activities, external vector storage, and retries. ## AI Model Risk Intelligence Know Which Models You Can Trust Before You Deploy DevFeed: [AI Model Risk Intelligence Know Which Models You Can Trust Before You Deploy]() Original publisher: [Read original article]() Author: Ranko Cupovic Published: 2026-08-04T04:00:00Z Content type: article Language: en Sources: [Blog RSS Feed | Snyk]() Topics: [Artificial Intelligence](), [Adversarial attacks](), [Security](), [asr](), [Benchmark](), [Deployment](), [pii](), [Code]() Tags: [ai](), [application-security](), [asr](), [attacks](), [awareness](), [benchmark](), [blog](), [deployment](), [developer](), [devops](), [enablement](), [model](), [pii](), [safety](), [security](), [snyk-platform](), [snyk-security-intel]() ### AI overview Evo's AI model risk score combines attack success rate and attack impact into a 0-1000 score. It is based on adversarial testing against standard system-prompt hardening and breaks risk down by attacker goals such as PII extraction, system-prompt extraction, and insecure code generation to support deployment decisions. ### Source excerpt AI model risk depends on how a model is deployed. Learn how Evo combines adversarial testing, attack impact, and deployment context to help teams compare models and enforce policy. ## Using Activity isolation as a security boundary DevFeed: [Using Activity isolation as a security boundary]() Original publisher: [Read original article]() Author: Houman Kargaran Published: 2026-08-04T00:00:00Z Content type: tutorial Language: en Sources: [Temporal Blog]() Topics: [Security](), [pii](), [Architecture & Design](), [MCP Server](), [data](), [Machine learning]() Tags: [community](), [engineering](), [isolation](), [mcp](), [mcp-server](), [ml](), [pii](), [security]() ### AI overview This guest post explains why a regulated application keeps PII scanning, classification, redaction, and storage within a single Temporal Activity. The design prevents sensitive data from crossing Activity boundaries and appearing in the Temporal UI, while using an in-house MCP server, an internal ML model, and a swappable storage layer. ### Source excerpt How keeping PII scan, classification, and storage inside one Temporal Activity stops raw data from ever crossing a boundary. ## The forbidden index: Building privacy-preserving search with OpenSearch DevFeed: [The forbidden index: Building privacy-preserving search with OpenSearch]() Original publisher: [Read original article]() Author: Kylie Wagar-Dirks Published: 2026-07-24T15:00:22Z Content type: article Language: en Sources: [OpenSearch]() Topics: [Open Source](), [Access Control](), [pii](), [dashboards](), [tokenization](), [data](), [elasticsearch](), [Framework]() Tags: [analytics](), [analytics-stack](), [blog](), [compliance](), [dashboards](), [data](), [dynamic-data](), [open-source](), [opensearch](), [pii](), [plugin](), [privacy](), [search](), [tokenization]() ### AI overview The article describes a talk by Unnati Mishra and Akshat Khanna on building privacy-preserving search and analytics with OpenSearch. Their approach moves privacy controls into the ingest layer, using a custom plugin to redact PII at index time through tokenization and dynamic data masking. It also applies differential privacy to OpenSearch Dashboards by adding calibrated noise to aggregate query results. ### Source excerpt At OpenSearchCon Europe 2026, Unnati Mishra and Akshat Khanna (Angel One) argued that privacy in search must be handled during the ingest phase rather than retroactively through access controls. The post The forbidden index: Building privacy-preserving search with OpenSearch appeared first on OpenSearch. ## Feature Flag Security in your CI/CD Pipeline DevFeed: [Feature Flag Security in your CI/CD Pipeline]() Original publisher: [Read original article]() Author: Lena Sano Published: 2026-07-22T00:00:00Z Content type: article Language: en Sources: [Harness Blog]() Topics: [feature flags](), [Security](), [CI/CD](), [AI Agent]() Tags: [ai-agent](), [ci-cd](), [cleanup](), [feature](), [feature-flagging](), [feature-flags](), [governance](), [lifecycle](), [local](), [pii](), [privacy](), [remote](), [security]() ### AI overview This article explains security practices for Harness Feature Management and Experimentation. It covers local versus remote feature-flag evaluation, privacy considerations for sensitive user data, governance, automated cleanup, and an AI agent for feature-flag lifecycle management. ### Source excerpt Secure feature flags with Harness FME using local or remote evaluation, automated cleanup, governance, and AI-powered lifecycle management. | Blog ## Beyond Redaction: Anatomy of a Privacy-Safe Data Platform DevFeed: [Beyond Redaction: Anatomy of a Privacy-Safe Data Platform]() Original publisher: [Read original article]() Author: Ananth Packkildurai Published: 2026-07-10T10:20:21Z Content type: tutorial Language: en Sources: [Data Engineering Weekly]() Topics: [data](), [pii](), [synthetic-data](), [Query (disambiguation)]() Tags: [data](), [encryption](), [engineering](), [pii](), [privacy](), [synthetic-data](), [tokenization]() ### AI overview This article explains why privacy-safe data platforms must preserve only the utility required for an approved purpose while controlling linkability and generating evidence that safeguards operated. It compares redaction, encryption, tokenization, governed views, aggregation, synthetic data, and clean-room access, emphasizing that deterministic tokens are generally pseudonymous rather than automatically anonymous. ### Source excerpt Why privacy engineering is about governing data in use--not simply hiding it. ## DigitalOcean Evaluations: Production Model and Router Testing for the Inference Stack DevFeed: [DigitalOcean Evaluations: Production Model and Router Testing for the Inference Stack]() Original publisher: [Read original article]() Author: Grace Morgan Published: 2026-07-01T15:41:47Z Content type: release Language: en Sources: [DigitalOcean]() Topics: [Digital Ocean](), [inference-endpoints](), [Large Language Model](), [model-deployment](), [Testing]() Tags: [configuration](), [cost](), [data](), [dataset](), [digitalocean](), [evaluation](), [inference](), [inference-endpoints](), [latency](), [llm](), [metric](), [model](), [models](), [performance](), [pii](), [product-updates](), [production](), [quality](), [router](), [testing](), [token]() ### AI overview DigitalOcean Evaluations adds production testing for models and inference router configurations in the DigitalOcean Inference Engine. Teams can run LLM-as-a-Judge evaluations on their own prompts and data, compare quality, latency, and cost, and use built-in or custom rubrics across models, imports, and router setups. ### Source excerpt Choosing the right model or inference router for production means more than reading a leaderboard. It means validating any model or routing configuration on your own data using your prompts and your evaluation criteria before it ever reaches production, and comparing quality, latency, and cost in one place. Evaluations, now available on the DigitalOcean Inference Engine, lets teams validate any model or inference router configuration on their own data before production. Run structured LLM-as-a-Judge evaluations across catalog models, fine-tuned models, BYOM imports, and router setups without stitching together a separate evaluation stack. DigitalOcean Evaluations Capabilities Evaluations provide everything teams need to validate model and router performance before production. LLM-as-a-Judge scoring runs across any candidate in your inference stack and returns per-item scores with judge rationale, plus latency, token, and cost tracking per run. Six pre-built metrics cover the most common evaluation needs out of the box. For teams that need full control: custom rubrics, reusable presets, MCP support, and full dataset management -- all in the same platform as the inference endpoints you use in production. View YouTube video Pre-Built and Custom Rubrics: Score Against Criteria That Match Your Domain The six pre-built metrics, correctness, completeness, faithfulness, PII, toxicity, and bias, cover common evaluation needs. For specialized domains, custom rubrics let teams define their own judge instructions and scoring criteria directly in the judge prompt. The judge evaluates responses against these criteria and returns per-item scores with rationale. Custom rubrics can also adapt the built-in correctness metric to different data formats instead of relying on a default interpretation. Evaluation Presets: Save Configurations and Re-Run Without Rebuilding Without saved configurations, every re-run becomes a rebuild with different judge models, parameters, or prompts, making ## Burp Extensibility 2026: Awards, Talks, and Highlights DevFeed: [Burp Extensibility 2026: Awards, Talks, and Highlights]() Original publisher: [Read original article]() Author: Fran Hutchings Published: 2026-06-19T12:18:14Z Content type: article Language: en Sources: [PortSwigger Blog]() Topics: [Extension](), [Reconnaissance](), [Authentication](), [Authorization](), [JSON Web Tokens](), [Vulnerabilities]() Tags: [auth](), [awards](), [community](), [discord](), [extension](), [pii](), [secrets](), [tokens](), [vulnerabilities](), [workshops]() ### AI overview PortSwigger's Extensibility Month highlighted Burp Suite extensions, Bambdas, and BChecks through talks, workshops, community sessions, and the 2026 Burp Extension Awards. The article summarizes the community-voted award process and notable tools for reconnaissance, authentication, access control, workflow manipulation, and vulnerability discovery. ### Source excerpt The 2026 Burp Suite Extension Awards Best Recon & Discovery Best Auth & Access Control Best Workflow & Manipulation Best API & Specialist Testing Hidden Gem Most Nominated The talks In ## Keycloak 26.6.2 released DevFeed: [Keycloak 26.6.2 released]() Original publisher: [Read original article]() Author: Keycloak Team Published: 2026-05-19T00:00:00Z Content type: release Language: en Sources: [Keycloak Blog]() Topics: [Keycloak](), [Vulnerabilities](), [Security](), [Authentication](), [OpenID connect (OIDC)](), [WebAuthn](), [XSS]() Tags: [2](), [2026](), [idm](), [kerberos](), [keycloak](), [keycloak-release](), [ldap](), [oidc](), [openid-connect](), [permission](), [pii](), [release](), [saml](), [security](), [sso](), [vulnerability](), [xss]() ### AI overview Keycloak 26.6.2 is a security-focused release that fixes multiple vulnerabilities, including denial-of-service issues, request smuggling, access-control flaws, stored XSS, WebAuthn policy bypass, token disclosure, account takeover, and PII enumeration. It also includes enhancements and bug fixes. ### Source excerpt To download the release go to Keycloak downloads. Upgrading Before upgrading refer to the migration guide for a complete list of changes. All resolved issues Security fixes #47485 CVE-2026-33871 HTTP/2 CONTINUATION Frame Flood Denial of Service #47486 CVE-2026-33870 RFC violation: HTTP Request Smuggling primitive via Chunked Extension Quoted-String Parsing #47932 [CVE-2026-4628] Improper Access Control on Keycloak Server through UMA resource management endpoints via PUT parameters authorization-services #48049 [CVE-2026-37980] Stored XSS in select-organization.ftl - FreeMarker HTML-escape insufficient in inline JS handler organizations #48275 CVE-2026-5588 Bouncy Castle Crypto Package For Java: Use of a Broken or Risky Cryptographic Algorithm vulnerability in bcpkix modules core #48388 [CVE-2026-6856] Acceptable AAGUID policy bypass via packed self-attestation in WebAuthn registration authentication/webauthn #48570 [CVE-2026-0636, CVE-2026-3505, CVE-2026-5598] Multiple bouncycastle CVEs core #49108 [CVE-2026-7307] Denial of service when sending a crafted request to the /saml endpoint #49109 [CVE-2026-7504] Security Vulnerability Report: Redirect URI Validation Bypass in Keycloak #49110 [CVE-2026-7571] Access token disclosure and implicit flow bypass via forged client data #49111 [CVE-2026-7507] Session fixation in OIDC login flow leading to account takeover #49112 [CVE-2026-37982] Execute-actions token replay allows unauthorized WebAuthn credential enrollment on victim account #49113 [CVE-2026-37979] OIDC Introspection endpoint does not enforce audience restriction, leaking claims from lightweight access tokens #49114 [CVE-2026-37978] Cross-role PII leakage via evaluate-scopes endpoints bypasses user view permission #49115 [CVE-2026-4630] Keycloak Authorization Services Protection API IDOR (Cross-Resource Server Access) #49116 [CVE-2026-37981] Broken Access Control in Account Resources User Lookup allows PII enumeration Enhancements #47728 Monitor backups for CNPG - ## A Story of Delayed AWS Pipelines DevFeed: [A Story of Delayed AWS Pipelines]() Original publisher: [Read original article]() Author: Vladimir Romashov Published: 2026-05-08T14:23:22Z Content type: article Language: en Sources: [Booking.com Development - Medium]() Topics: [Amazon Web Services](), [Terraform](), [AWS Organizations](), [Infrastructure as code](), [CI/CD](), [Security]() Tags: [aws](), [aws-organizations](), [booking](), [ci-cd](), [ci-cd-pipeline](), [infrastructure-as-code](), [pii](), [terraform]() ### AI overview The article investigates delays in Terraform CI/CD pipelines caused by repeated use of the aws_organizations_organization data source and interactions with the AWS Organizations API. Testing found that roughly 1 in 10 Terraform pipelines were affected, with delays ranging from 1 to 15 minutes, while comparable CDK pipelines were not delayed. ### Source excerpt How a seemingly simple AWS API call can silently slow down your CI/CD pipelines Review/co-researcher: Gonzalo Ulla The Mystery It started with a line in one of our team's CI/CD logs that nobody expected: module.project.module.user_buckets.module.s3_bucket.data.aws_organizations_organization.current: Still reading... [15m10s elapsed] 15 minutes and 10 seconds -- just to read organization data. A value that should return in milliseconds was holding up entire pipelines. After digging deeper, we discovered this wasn't a one-off issue. During testing, roughly 1 in 10 pipelines containing Terraform were affected, with delays ranging from 1 to 15 minutes each. At Booking.com, we deploy and manage our AWS infrastructure using two primary Infrastructure as Code (IaC) technologies: Terraform and AWS Cloud Development Kit (CDK). To standardize and enforce our compliance and security controls, we maintain a set of internal Terraform and CDK modules to provision resources that handle personally identifiable information (PII). Interestingly, only Terraform pipelines were affected by this issue -- CDK ones running in the same accounts and against the same AWS Organization were completed without any delays. [spoiler alert/] CDK uses CloudFormation under the hood, which doesn't make additional Organizations API calls directly. [/spoiler alert]. This ruled out a general AWS-side outage or account-level throttling and pointed us toward something specific to how Terraform interacts with the Organizations API. This is the story of how we tracked down the root cause -- and why the fix isn't as simple as you'd think. What is aws_organizations_organization? Terraform's aws_organizations_organization data source retrieves information about, guess what, your AWS Organization. On the surface, it maps to the AWS DescribeOrganization API call -- a flat request. No iteration. No pagination. Simple... Or so we thought. The First Clue: Reproducing the Issue The references to the Organizations API mostly c ## How to build scalable web apps with OpenAI's Privacy Filter DevFeed: [How to build scalable web apps with OpenAI's Privacy Filter]() Original publisher: [Read original article]() Author: yuvraj sharma; Freddy Boulton; Abubakar Abid Published: 2026-04-27T00:00:00Z Content type: tutorial Language: en Sources: [Hugging Face - Blog]() Topics: [privacy-filter](), [gradio](), [Web](), [Artificial Intelligence](), [OpenAI](), [Canvas]() Tags: [apache](), [artificial-intelligence](), [benchmark](), [gradio](), [html](), [openai](), [pii](), [privacy-filter](), [web-apps]() ### AI overview An article about building scalable web apps with OpenAI's Privacy Filter. It presents document, image, and text-redaction applications built with Gradio, including PII highlighting, image annotations, redaction links, custom HTML/JavaScript frontends, queued endpoints, and ZeroGPU allocation. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Introducing OpenAI Privacy Filter DevFeed: [Introducing OpenAI Privacy Filter]() Original publisher: [Read original article]() Published: 2026-04-22T00:00:00Z Content type: article Language: en Sources: [OpenAI News]() Topics: [privacy-filter](), [pii](), [Artificial Intelligence](), [Security](), [Software]() Tags: [ai](), [benchmark](), [developers](), [infrastructure](), [model](), [open](), [openai](), [pii](), [privacy](), [privacy-filter](), [research](), [security](), [software](), [workflows]() ### AI overview OpenAI introduces Privacy Filter, a small open-weight model that detects and redacts personally identifiable information in unstructured text. It supports context-aware, local, high-throughput processing and can be fine-tuned for privacy workflows. ### Source excerpt OpenAI Privacy Filter is an open-weight model for detecting and redacting personally identifiable information (PII) in text with state-of-the-art accuracy ## Architectural Bets for More Governable and Reliable Production Agent Systems DevFeed: [Architectural Bets for More Governable and Reliable Production Agent Systems]() Original publisher: [Read original article]() Author: Addy Osmani Published: 2026-04-18T17:16:43Z Content type: opinion Language: en Sources: [Elevate]() Topics: [Architecture & Design](), [Security](), [Authorization](), [systems]() Tags: [agent](), [agentic](), [api](), [audit](), [autonomous](), [governance](), [identity](), [incident](), [pii](), [security]() ### AI overview This opinion article argues that production agent systems face a stack ceiling caused by fragile session logic, shared credentials, weak governance, and unreliable downstream dependencies. It proposes architectural changes, beginning with giving agents distinct platform-level identities instead of shared service accounts or inherited OAuth tokens. ### Source excerpt The bet every serious developer needs to make on on their agent stack ## Как маскировать персональные данные на изображениях: наш эксперимент с OCR и NER DevFeed: [Как маскировать персональные данные на изображениях: наш эксперимент с OCR и NER]() Original publisher: [Read original article]() Author: andrivasg (red\_mad\_robot) Published: 2026-03-17T15:55:37Z Content type: tutorial Language: ru Sources: [Redmadrobot EN](), [Redmadrobot RU]() Topics: [Natural language processing](), [pii]() Tags: [ai](), [computer-vision](), [llm](), [ner](), [nlp](), [ocr](), [pii](), [red-mad-robot](), [rnd](), [tag-601fbc7112a4](), [tag-7bc388df28ed](), [tag-9bf5e01ce62e](), [tag-b92bf5906bbd](), [tag-ef0b1bf200df]() ### AI overview The article describes red_mad_robot's experiment using OCR combined with a NER model to detect and selectively mask personally identifiable information in images without training specialized visual detectors. On a dataset of 40 annotated images, the pipeline masked 90% of personal data while falsely masking 14% of text polygons; performance declined on difficult real-world photographs. ### Source excerpt Всем привет! Меня зовут Андрей Иванов, я NLP-исследователь в R&D red_mad_robot. Мы разрабатываем систему Guardrails для защиты персональных данных (PII) и фильтрации небезопасного контента. В этой статье расскажу, как мы решали задачу точечного маскирования PII на картинках без обучения специальных визуальных детекторов. Разберём связку оптического распознавания символов (OCR) с NER-моделью, покажем метрики на реальных данных, раскроем ограничения подхода и наши решения для их преодоления. Читать далее ## How AI firewalls protect production applications from prompt injection, data leakage, and excessive usage DevFeed: [How AI firewalls protect production applications from prompt injection, data leakage, and excessive usage]() Original publisher: [Read original article]() Author: Alex Ewerlöf Published: 2026-03-15T23:51:29Z Content type: tutorial Language: en Sources: [Alex Ewerlof Notes]() Topics: [Firewall](), [Security](), [prompt injection](), [LLMs](), [rate-limiting](), [pii]() Tags: [architecture](), [firewall](), [llms](), [pii](), [prompt-injection](), [rate-limiting](), [security]() ### AI overview This tutorial explains AI firewalls, or AI gateways, as reverse proxies with AI-focused inspection between an application backend and an inference provider. It covers ingress attacks such as prompt injection, egress risks including PII and secrets, rate limiting to control costs, latency considerations, implementation trade-offs, and layered defenses. ### Source excerpt How to protect your AI application in production against new classes of attacks ## Building transactional voice agents at Nector DevFeed: [Building transactional voice agents at Nector]() Original publisher: [Read original article]() Author: Pranshu Raj Published: 2026-03-07T13:39:58Z Content type: article Language: en Sources: [Pranshu Raj - blog on backend systems, performance and sidequests]() Topics: [Model Context Protocol](), [Latency](), [Multi-tenancy](), [Back end](), [observability](), [Database]() Tags: [agents](), [api](), [backend](), [database-design](), [json-rpc](), [latency](), [latency-optimization](), [mcp](), [multi-tenancy](), [observability](), [pii](), [production](), [proxy](), [rest-api](), [voice]() ### AI overview An engineer describes building customer-facing transactional voice agents for ecommerce at Nector. The article covers a REST-to-JSON-RPC MCP proxy that improved observability, PII control, context reduction, latency, and correctness, plus experiments that reduced one agent's p90 latency from more than 8 seconds to 2 seconds. ### Source excerpt Building production ready voice agents, latency optimization, multi tenancy, MCP proxies - six months of building customer facing voice agents ## Introducing Iceberg output for Redpanda Connect DevFeed: [Introducing Iceberg output for Redpanda Connect]() Original publisher: [Read original article]() Author: Prakhar Garg Published: 2026-03-05T00:00:00Z Content type: release Language: en Sources: [Redpanda]() Topics: [Apache Iceberg](), [Redpanda-Connect](), [Streaming](), [Routing (disambiguation)](), [schema-evolution](), [YAML](), [data]() Tags: [apache-iceberg](), [connectors](), [integration](), [pii](), [redpanda-connect](), [routing](), [schema-evolution](), [streaming](), [yaml]() ### AI overview Redpanda introduces an Iceberg output for Redpanda Connect that writes streaming data directly to Apache Iceberg tables through declarative YAML pipelines. The component supports transformations, enrichment, PII removal, and content-based routing across Redpanda Connect inputs and processors, enabling data from sources such as HTTP webhooks, Postgres CDC streams, and GCP Pub/Sub to reach lakehouse tables with less infrastructure and configuration overhead. ### Source excerpt Land any data into Apache Iceberg with Redpanda Connect. Maximize infra density, automate schema evolution, and scale 1-to-many routing without the toil. [Next page]()