MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair

arXiv:2607.27080 · cs.CR, cs.AI · Submitted 2026-07-29 · Read on arXiv

Xuanze Chen, Xukang Xie, Wentao Fu, Jiajun Zhou, Shanqing Yu, Qi Xuan

cs.CR, cs.AI

Submitted: 2026-07-29

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 37× in this paper · explained in 2 episodes
• Agent Harness — 15× in this paper · explained in 2 episodes
• Consistency — 11× in this paper · explained in 3 episodes
• Agent Memory — 10× in this paper · explained in 1 episode
• Core — 10× in this paper · explained in 2 episodes
• Trace — 7× in this paper · explained in 2 episodes
• Provenance — 6× in this paper · explained in 4 episodes
• Verifier — 6× in this paper · explained in 2 episodes
• Accuracy — 5× in this paper · explained in 1 episode
• Admissibility — 5× in this paper · explained in 2 episodes
• Aggregation — 4× in this paper · explained in 1 episode
• Benchmarking — 3× in this paper · explained in 4 episodes
• Fidelity — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Grounding — 2× in this paper · explained in 3 episodes
• Structural Integrity — 2× in this paper · explained in 3 episodes
• Verification — 2× in this paper · explained in 2 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Clustering — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Information Asymmetry — 1× in this paper · explained in 2 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• Memory Exploitation Success Rate — 1× in this paper
• Memory Poisoning Success Rate — 1× in this paper
• Selective Repair Success Rate — 1× in this paper
• Steering — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
• Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
• Trojan Hippo Bench: A Dynamic Benchmark for Persistent Memory Attacks and Defenses in LLM Agents
• From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents
• A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle
• Securing LLM-Agent Long-Term Memory Against Poisoning: Non-Malleable, Origin-Bound Authority with Machine-Checked Guarantees
• Hidden in Memory: Sleeper Memory Poisoning in LLM Agents
• MemLeak: Diagnosing Information Leaks in Multimodal Agent Memory
• LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
• MemEvoBench: Benchmarking Safety Risks from Memory Misevolution in LLM Agents
• From Storage to Steering: Memory Control Flow Attacks on LLM Agents
• MemMorph: Tool Hijacking in LLM Agents via Memory Poisoning
• Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs