MRMMIA is a multi-recall-probe membership inference attack that extracts signals from chat agent memory and outperforms baselines in black-, gray-, and white-box settings.
Unveiling privacy risks in llm agent memory
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
A new 7x4 taxonomy organizes agentic AI security threats by architectural layer and persistence timescale, revealing under-explored upper layers and missing defenses after surveying 116 papers.
Proposes an OS-centered privacy framework for on-device AI that treats privacy as institutional accountability, including a threat model, six-part risk taxonomy, privacy-by-architecture controls, and four-level audit rubric demonstrated on Apple, Android, and Microsoft systems.
Memory-equipped LLM agents exhibit increasing safety violation rates as memory accumulates across independent tasks, termed temporal memory contamination, detected via a new trigger-probe protocol.
ADAM extracts data from LLM agent memory with up to 100% attack success rate by estimating data distribution and selecting queries via entropy guidance.
A data-centric survey finds that only information-flow control covers compositional and cross-session leakage in LLM agents and that no single benchmark tests an agent across all its data surfaces under one policy.
The paper defines four governance primitives for shared memory in multi-agent LLM fleets and reports evaluation results from a live production service.
ALDEN boosts private data extraction rates from RAG systems by combining active learning for query diversification with dynamic estimation of the underlying knowledge-base topic distribution.
The paper surveys human memory categories, maps them to LLM memory, and proposes a new three-dimension (object, form, time) categorization into eight quadrants to organize existing work and highlight open problems.
The paper delivers the first systematic review of self-evolving agents, structured around what components evolve, when adaptation occurs, and how it is implemented.
A survey that deconstructs LLM agent systems via a methodology-centered taxonomy linking design principles to emergent behaviors, applications, and challenges.
citing papers explorer
-
MRMMIA: Membership Inference Attacks on Memory in Chat Agents
MRMMIA is a multi-recall-probe membership inference attack that extracts signals from chat agent memory and outperforms baselines in black-, gray-, and white-box settings.
-
A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework
A new 7x4 taxonomy organizes agentic AI security threats by architectural layer and persistence timescale, revealing under-explored upper layers and missing defenses after surveying 116 papers.
-
Local Is Not a Sufficient Privacy Boundary: Governing OS-Integrated On-Device AI
Proposes an OS-centered privacy framework for on-device AI that treats privacy as institutional accountability, including a threat model, six-part risk taxonomy, privacy-by-architecture controls, and four-level audit rubric demonstrated on Apple, Android, and Microsoft systems.
-
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
Memory-equipped LLM agents exhibit increasing safety violation rates as memory accumulates across independent tasks, termed temporal memory contamination, detected via a new trigger-probe protocol.
-
ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying
ADAM extracts data from LLM agent memory with up to 100% attack success rate by estimating data distribution and selecting queries via entropy guidance.
-
Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents
A data-centric survey finds that only information-flow control covers compositional and cross-session leakage in LLM agents and that no single benchmark tests an agent across all its data surfaces under one policy.
-
Governed Shared Memory for Multi-Agent LLM Systems
The paper defines four governance primitives for shared memory in multi-agent LLM fleets and reports evaluation results from a live production service.
-
ALDEN: Boosting Private Data Extraction from Retrieval-Augmented Generation Systems via Active Learning and Distribution Estimation
ALDEN boosts private data extraction rates from RAG systems by combining active learning for query diversification with dynamic estimation of the underlying knowledge-base topic distribution.
-
From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs
The paper surveys human memory categories, maps them to LLM memory, and proposes a new three-dimension (object, form, time) categorization into eight quadrants to organize existing work and highlight open problems.
-
A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence
The paper delivers the first systematic review of self-evolving agents, structured around what components evolve, when adaptation occurs, and how it is implemented.
-
Large Language Model Agent: A Survey on Methodology, Applications and Challenges
A survey that deconstructs LLM agent systems via a methodology-centered taxonomy linking design principles to emergent behaviors, applications, and challenges.