REVIEW 5 cited by
Unveiling Privacy Risks in LLM Agent Memory
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Large Language Model (LLM) agents have become increasingly prevalent across various real-world applications. They enhance decision-making by storing private user-agent interactions in the memory module for demonstrations, introducing new privacy risks for LLM agents. In this work, we systematically investigate the vulnerability of LLM agents to our proposed Memory EXTRaction Attack (MEXTRA) under a black-box setting. To extract private information from memory, we propose an effective attacking prompt design and an automated prompt generation method based on different levels of knowledge about the LLM agent. Experiments on two representative agents demonstrate the effectiveness of MEXTRA. Moreover, we explore key factors influencing memory leakage from both the agent designer's and the attacker's perspectives. Our findings highlight the urgent need for effective memory safeguards in LLM agent design and deployment.
Forward citations
Cited by 5 Pith papers
-
Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents
Malicious tools can systematically extract isolated LLM-agent long-term memory via persistence, pure-anchor retrieval steering, and reactivation payloads, reaching 80% extraction with unlimited triggers and 47% with 20.
-
Towards Aligning Personalized Conversational Recommendation Agents with Users' Privacy Preferences
Privacy management for conversational AI agents is reframed as a dynamic alignment problem in which agents learn a user's latent privacy-utility reward function from feedback.
-
LLM Agents Should Employ Security Principles
A position paper proposing AgentSandbox, a framework that applies Saltzer-Schroeder security principles to LLM agents and reports large attack-success-rate reductions on AgentDojo.
-
A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents
The paper surveys security risks of LLM agents, organizes them into a five-level autonomy taxonomy, and proposes an untested CMDP-based architecture called R2A2.
-
A Survey on Agent Workflow -- Status and Future
A review that classifies 24 agent workflow systems along functional and architectural axes and argues for standardization, optimization, and security work.
Discussion (0). Sign in to comment.