MemoryDojo: Benchmarking Poisoning Through LLM Agent Memory
cs.CR, cs.AI, cs.CL
Submitted: 2026-11-06
Updated: 2026-11-06
Terminology
Sources
- Phantom: General Backdoor Attacks on Retrieval Augmented Language Generation
- From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents
- Defeating Prompt Injections by Design
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- MemPoison: Uncovering Persistent Memory Threats and Structural Blind Spots in LLM Agents
- HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models
- MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks
- AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks
- MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Models
- GraphRAG under Fire
- A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle
- MemGPT: Towards LLMs as Operating Systems
- Zep: A Temporal Knowledge Graph Architecture for Agent Memory
- When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents
- LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
- Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity
- What If Prompt Injection Never Left? Rethinking Agent Security through Cross-Session Stored Prompt Injection
- AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications
- Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents
Related papers
- From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
- Privacy Leakage from Recurrent State in LLM Inference
- Incrementally Verifiable Oracle Aided Computation
- Privilege and confidentiality in generative AI workflows
- BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts
- CoVault: Secure, Scalable Analytics of Personal Data