MemForm: Benchmarking Memory Formation Poisoning in LLM Agents
cs.CR, cs.CL
Submitted: 2026-10-10
Updated: 2026-10-10
Code: https://github.com/opanhw/memform-code
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents
- Memory Injection Attacks on LLM Agents via Query-Only Interaction
- MemPoison: Uncovering Persistent Memory Threats and Structural Blind Spots in LLM Agents
- Your Agent's Memories Are Not Its Own: Forged Reasoning Attacks on LLM Agent Memory and Defenses
- A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle
- MemGPT: Towards LLMs as Operating Systems
- Hidden in Memory: Sleeper Memory Poisoning in LLM Agents
- Memory Poisoning Attack and Defense on Memory Based LLM-Agents
- MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly Detection
- OEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable Experiences
- SafeGuard: A Multi-Agent Perception-Reasoning Framework for Social-Risk AI-Generated Video Detection
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- From Storage to Steering: Memory Control Flow Attacks on LLM Agents
- GLM-5: from Vibe Coding to Agentic Engineering
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
- Estimating the Social Cost of Corporate Data Breaches
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills