Understanding Stage-Wise Utility-Risk Trade-offs in LLM Agent Memory
cs.CR
Submitted: 2026-08-31
Updated: 2026-08-31
Terminology
Sources
- ER-MIA: Black-Box Adversarial Memory Injection Attacks on Long-Term Memory-Augmented Large Language Models
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval
- From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents
- LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
- Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections
- Hindsight is 20/20: Building Agent Memory that Retains, Recalls, and Reflects
- A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle
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