# agent privacy

Published articles for agent privacy.

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

## Judging Before Propagation: Task-Graph Contextual Integrity for Multi-Agent Privacy

DevFeed: [Judging Before Propagation: Task-Graph Contextual Integrity for Multi-Agent Privacy](<https://devfeed.tech/articles/judging-before-propagation-task-graph-contextual-integrity-for-multi-agent-privacy-108207.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.39532>)

Author: Hengyu Wu, Blaise Delattre, Yang Cao

Published: 2026-10-30T04:00:00Z

Content type: news

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: [Security & Privacy](<https://devfeed.tech/topics/security-privacy.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Access Control](<https://devfeed.tech/topics/access-control.md>), [agent to agent communication](<https://devfeed.tech/topics/agent-to-agent-communication.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-privacy](<https://devfeed.tech/tags/agent-privacy.md>), [authorization](<https://devfeed.tech/tags/authorization.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [disclosure](<https://devfeed.tech/tags/disclosure.md>), [graph](<https://devfeed.tech/tags/graph.md>), [integrity](<https://devfeed.tech/tags/integrity.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>), [privacy](<https://devfeed.tech/tags/privacy.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

Task-Graph Contextual Integrity (TG-CI) authorizes information releases by considering both an item's intended downstream scope and recipients' evolving disclosure histories across a multi-agent task graph. This addresses a gap in local Contextual Integrity checks, which can approve a disclosure at one boundary without accounting for later propagation. Full-Scope requires admissibility across the complete downstream scope; Auto-Region confines an item to its maximal admissible region using frontier gates. On MAPLE-Bench, a 144-case benchmark spanning four scenarios, the primary configuration reduced mean unauthorized disclosures by 85.8-94.1% versus the Local-History CI baseline while retaining 93.6-96.1% of its task accuracy. The authors report complementary privacy, cost, and utility trade-offs between the policies.

### Source excerpt

arXiv:2610.39532v1 Announce Type: cross Abstract: Multi-agent LLM systems increasingly rely on persistent memory and inter-agent communication. These capabilities create privacy risks that extend beyond individual interactions: a release appropriate in isolation may become inappropriate when combined with information previously disclosed to a recipient or propagated to downstream agents along the planned workflow. Existing Contextual Integrity (CI) mechanisms for agentic systems typically rely on local judgments that assess each disclosure in isolation, with or without regard to the recipient's history, but do not account for how information propagates downstream. However, compliance at the current boundary does not guarantee appropriateness across the workflow. We introduce Task-Graph Contextual Integrity (TG-CI), to our knowledge the first task-graph-native formalization of Contextual Integrity for multi-agent systems. TG-CI represents a workflow as a Multi-Agent Task Graph (MATG) and extends CI from atomic transfers to stateful, graph-level information flows by jointly considering an item's intended propagation scope and recipients' evolving disclosure states. We operationalize TG-CI through propagation-scoped authorization under two complementary policies: Full-Scope, which requires admissibility across the complete downstream scope, and Auto-Region, which confines each item to its maximal admissible region using lightweight frontier gates. We further introduce MAPLE-Bench, a benchmark of 144 cases across four scenarios that jointly vary MATG topology, disclosure history, compromised-agent placement, and item-level privacy policies. In our primary experimental configuration, TG-CI reduces the mean unauthorized disclosure count by 85.8-94.1% relative to the Local-History CI baseline, while retaining 93.6-96.1% of the baseline's task accuracy, with the two enforcement policies providing complementary privacy--cost--utility trade-offs.

## Indistinguishable Agents: Training Agent Privacy as Twin-World Indistinguishability

DevFeed: [Indistinguishable Agents: Training Agent Privacy as Twin-World Indistinguishability](<https://devfeed.tech/articles/indistinguishable-agents-training-agent-privacy-as-twin-world-indistinguishability-93433.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.25161>)

Author: Jiaming He, Guanyu Hou, Yi Yu, Xudong Jiang

Published: 2026-10-21T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Security & Privacy](<https://devfeed.tech/topics/security-privacy.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [grpo](<https://devfeed.tech/topics/grpo.md>), [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>)

Tags: [agent-privacy](<https://devfeed.tech/tags/agent-privacy.md>), [agents](<https://devfeed.tech/tags/agents.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [grpo](<https://devfeed.tech/tags/grpo.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-agents](<https://devfeed.tech/tags/llm-agents.md>), [privacy](<https://devfeed.tech/tags/privacy.md>), [training](<https://devfeed.tech/tags/training.md>)

### AI overview

The paper proposes training LLM agents to limit what observers can infer from their actions, not just what they explicitly disclose. It creates paired "twin worlds" differing only in a private fact; a frozen distinguisher scores each observer's view by its log-likelihood ratio for the true world, and paired GRPO optimizes task success minus that score. The authors say the objective controls every observer's Bayes success across channels. In shopping and messaging tasks, the method reportedly reduces leakage missed by disclosure judges and query-level rewards while preserving task completion.

### Source excerpt

arXiv:2610.25161v1 Announce Type: new Abstract: LLM agents search, shop and send messages for their users, and every action is seen by some party. Existing privacy training rewards agents for not mentioning protected items, yet an observer can infer a private fact from what the agent does. Since an observer learns a fact only if its view changes with the fact, we propose \methodfull (\method), which trains on twin worlds that differ only in the private fact. A frozen distinguisher scores each observer's view by its log-likelihood ratio for the true world, and paired GRPO trains the agent on task success minus this ratio. We prove that this objective controls the Bayes success of every observer on every channel. On shopping and messaging tasks \method removes the leakage that disclosure judges and query-level rewards miss, while the agent still completes its tasks.

## Meta teams up with Bret Taylor's Sierra Technologies on new standards for AI agent commerce

DevFeed: [Meta teams up with Bret Taylor's Sierra Technologies on new standards for AI agent commerce](<https://devfeed.tech/articles/meta-teams-up-with-bret-taylor-s-sierra-technologies-on-new-standards-for-ai-agent-commerce-66431.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/10/06/meta-teams-up-with-bret-taylors-sierra-technologies-on-new-standards-for-ai-agent-commerce/>)

Author: Mike Wheatley

Published: 2026-10-07T00:54:21Z

Content type: news

Language: en

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

Topics: [agent to agent communication](<https://devfeed.tech/topics/agent-to-agent-communication.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Single sign-on (SSO)](<https://devfeed.tech/topics/sso.md>)

Tags: [agent-privacy](<https://devfeed.tech/tags/agent-privacy.md>), [agentic-commerce](<https://devfeed.tech/tags/agentic-commerce.md>), [agentic-security](<https://devfeed.tech/tags/agentic-security.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agent-commerce](<https://devfeed.tech/tags/ai-agent-commerce.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [apis](<https://devfeed.tech/tags/apis.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [bret-taylor](<https://devfeed.tech/tags/bret-taylor.md>), [industry-standards](<https://devfeed.tech/tags/industry-standards.md>), [meta](<https://devfeed.tech/tags/meta.md>), [meta-platforms](<https://devfeed.tech/tags/meta-platforms.md>), [news](<https://devfeed.tech/tags/news.md>), [online](<https://devfeed.tech/tags/online.md>), [online-commerce](<https://devfeed.tech/tags/online-commerce.md>), [personal-agent-protocol](<https://devfeed.tech/tags/personal-agent-protocol.md>), [personal-ai-agents](<https://devfeed.tech/tags/personal-ai-agents.md>), [salesforce](<https://devfeed.tech/tags/salesforce.md>), [security-concerns](<https://devfeed.tech/tags/security-concerns.md>), [sierra-technologies](<https://devfeed.tech/tags/sierra-technologies.md>), [stripe](<https://devfeed.tech/tags/stripe.md>), [the-latest](<https://devfeed.tech/tags/the-latest.md>), [walmart](<https://devfeed.tech/tags/walmart.md>)

### AI overview

Meta, Sierra Technologies, Walmart and Stripe are developing the Personal Agent Protocol, a proposed standard for identifying and governing AI agents as they interact with businesses online. The effort addresses authentication, consumer authorization, visibility and safety concerns around agent-led purchases.

### Source excerpt

Meta Platforms Inc. is partnering with Walmart Inc., Stripe Inc. and the enterprise artificial intelligence firm Sierra Technologies Inc. on the creation of new standards that will define how autonomous AI agents interact with other businesses online. The new standard was introduced by Sierra co-founder Bret Taylor, the former co-chief executive of Salesforce Inc., who [...] The post Meta teams up with Bret Taylor's Sierra Technologies on new standards for AI agent commerce appeared first on SiliconANGLE.