arXiv AI

Authorization Before Context: A Model-Neutral Audience Boundary Against Cross-Audience Memory Leakage in Agentic Systems

The paper proposes an "authorization before context" rule to prevent cross‑audience memory leakage in personal language agents. Each memory item is tagged with the audience that recorded it, and when assembling context for a new audience, the system only includes items whose original audience fully overlaps the current viewers. The authors prove that this rule guarantees that no fact recorded for a narrower audience can appear in a broader one, and they demonstrate its effectiveness on a synthetic Contextual‑Integrity benchmark.

arXiv AI

4d ago

Audience-Bound Persistent Memory: Authorization Across the Memory Lifecycle

The paper introduces Audience‑Bound Persistent Memory, a system that tracks the audience of each memory item and enforces authorization throughout the memory lifecycle. Each item carries the audience present at recording, and derived items are partitioned or suppressed based on the intersection of source audiences, expanding only through explicit grants. The authors implement the approach in two reference architectures—a flat store and a relationship graph—and evaluate it on 10,000 multi‑party histories, showing that no forbidden items entered any context while unscoped retrieval exposed forbidden items in 82% of cases, and that entitled recall matched policy‑equivalent baselines and outperformed unscoped retrieval by 0.30 Recall@5.

By Sibo Liu

agents

arXiv AI

Jun 26

Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents

arXiv:2606. 26627v1 Announce Type: cross Abstract: Large language model agents increasingly query databases, search document collections, call external APIs, remember past interactions, and act on a user's behalf.

By Nada Lahjouji, Ashwin Gerard Colaco

llms rag agents benchmarks safety data-engineering

arXiv AI

Jun 16

FragFuse: Bypassing Access Control of Large Language Model Agents via Memory-Based Query Fragmentation and Fusion

arXiv:2606. 15609v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly rely on long-term memory to support complex task execution, user personalization, and domain adaptation.

By Zixin Rao, Wentian Zhu, Chan Aristella Lu, Zhaorun Chen, Wei Niu, Le Guan, Bo Li, Zhen Xiang

llms agents fine-tuning benchmarks

arXiv AI

Jul 9

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents

arXiv:2607. 06595v1 Announce Type: cross Abstract: Personal AI agents powered by large language models can reason and act using available tools to access emails, manage calendars, and push code to remote repositories, all with minimal oversight.

By George Torres, Sharad Shrestha, Satyajayant Misra

llms agents benchmarks

Hugging Face Trending Papers

Aug 3

MNC: Scope-Bound Semantic Declassification for Private LLM-Agent Communication

Multi-agent large language model (LLM) systems can expose protected state through internal messages, tool arguments, logs, and persistent memory even when their public outputs appear innocuous. Existing privacy prompts, redaction methods, and source-level access controls restrict surface content or data access, but do not specify what a legitimately informed agent should disclose or how that disclosure may be reused downstream.

llms agents safety

arXiv Machine Learning

Sep 3

Context Inference Attacks Without Jailbreaks

The paper investigates privacy risks in agentic AI systems that assemble sensitive data into a hidden context before responding. It introduces context‑inference attacks, a security game that evaluates how well attackers can recover this hidden context under varying levels of knowledge and indirect delivery. Experiments show that even with controls such as instructions not to disclose, logit suppression, and context dilution, agents can leak significant contextual information, achieving high success rates across multiple attack settings.

By Prince Jha, Samuele Poppi, Nils Lukas

agents multimodal safety

arXiv AI

Jun 30

Governance Decay: How Context Compaction Silently Erases Safety Constraints in Long-Horizon LLM Agents

arXiv:2606. 22528v2 Announce Type: replace Abstract: Modern LLM agents increasingly rely on context compaction, summarization, or eviction to keep long-running sessions within a token budget.

By Shiyang Chen

llms agents nlp benchmarks safety

arXiv AI

Sep 15

Confuse the Model, Control the Flow: Understanding and Mitigating Privacy Leakage from LLM Agents with Information Flow Control

arXiv:2609.14003v1 Announce Type: cross Abstract: Personal AI agents built on large language models (LLMs) are increasingly given access to a user's private data and communications in order to provid...

By Minsun Shim, Ramisha Raida Karim, Ruthwik Jakkula, Kaiwen Zhou, Xin Liu, Xin Eric Wang, Zhou Li

llms agents benchmarks safety

arXiv Machine Learning

Aug 21

Inadvertent Context Leakage in Language Models

arXiv:2608. 19857v1 Announce Type: new Abstract: For AI agents to be useful beyond simple chat, they must hold sensitive user context such as calendars, credentials, health records, and financial data.

By Jaiden Fairoze, Neal Mangaokar, Kamalika Chaudhuri, Sanjam Garg, Saeed Mahloujifar

llms agents reinforcement-learning safety

arXiv Machine Learning

Aug 5

DP-MemView: A Memory Interface for Attribute-Level Transcript Privacy in Long-Term LLM Agents

arXiv:2608. 03130v1 Announce Type: cross Abstract: Long-term memory enables persistent personalization in LLM agents, but repeated memory-conditioned responses can cumulatively reveal protected attributes even when they are never stated explicitly.

By Jong Wook Kim, Byoungjae Min, Kennedy Edemacu, Yoonhyuk Choi, Sae-Hong Cho, Beakcheol Jang

llms agents benchmarks safety

arXiv AI

Jul 3

ElephantAgent: Contextual State Continuity in Agentic Systems

arXiv:2607. 01919v1 Announce Type: new Abstract: Agentic systems enhance their capabilities by invoking external tools and maintaining persistent memory.

By Jiankai Jin, Xiangzheng Zhang, Zhao Liu, Wenzhuo Xu, Dongdong Yang, Deyue Zhang, Quanchen Zou

agents safety

arXiv AI

Sep 10

MeClear: Cooperative Game-Theoretic Attribution and Risk-Aware Memory Clearance for Long-Horizon LLM Agents

arXiv:2609.09115v1 Announce Type: new Abstract: Long horizon Large Language Model (LLM) agents rely on external memory systems to preserve user preferences and task knowledge across extended interact...

By Boyu Yang, Jiazheng Sun, Zilong Lu, Zhi Qiu, Xin Peng, Jun Zheng

llms agents

Related stories