MemForm: Benchmarking Memory Formation Poisoning in LLM Agents

Reported by arXiv cs.CR (Haowen Pan, Pengyang Shao, Yunshan Ma, Yanzheng Jin, Naixin Zhai, Xiang Wang, Xun Yang)

Summary by Cyber Security News14 Oct 2026, 06:00 CEST

About this summary. This is a short, independently written summary of an article first published by arXiv cs.CR. Cyber Security News did not report or verify the underlying story. Read the original: https://arxiv.org/abs/2610.14431

arXiv:2610.14431v1 Announce Type: new Abstract: Long-term memory enables LLM agents to learn from past interactions but exposes memory formation to adversarial influence. Existing studies primarily organize memory poisoning by attack channels, corruption patterns, or lifecycle stages, leaving formation interfaces insufficiently characterized.

Read the full article at arXiv cs.CR →

Source attribution: headline and facts are from arXiv cs.CR (arxiv.org). Summary method: excerpt of the source description. See our source attribution policy.

Related coverage

INFUSE: A Unified Surface Benchmark for Indirect Prompt Injection in Agentic Systems

GitHub adopts cheaper AI model to catch secrets developers leave in code

APEX: Active Protection at Execution Boundaries for LLM Agents

Understanding and Enhancing Backdoor Persistency in LLM Agent Post-Training

HarnessSecurity-Bench: Do Security Mechanisms Really Protect Coding Agent Harnesses?

SkillPoison: Progressive Skill Poisoning via Successful Experiences