Research · curated 8 Sep 2026

Hidden in Memory: Sleeper Memory Poisoning in LLM Agents

Coverage timeline

discovered arxiv.org primary 5 Sep 2026medium.com 8 Sep 2026theconversation.com

Why it matters

Sleeper memory poisoning turns an AI agent's persistent memory into a long-term, dormant attack surface that can silently steer decisions across many later sessions, evading defenses focused only on single-prompt injection.

Research paper 'Hidden in Memory: Sleeper Memory Poisoning in LLM Agents' (arXiv:2605.15338) demonstrates a delayed attack in which adversarial content in an external document, webpage, or repository causes a stateful LLM assistant to store a fabricated memory that re-emerges across future conversations. Across tested assistants, poisoned memories were written up to 99.8% on GPT-5.5 and 95% on Kimi-K2.6, and successful retrievals steered attacker-intended agentic actions in 60-89% of cases; a Medium explainer summarizes the concept and defenses.