InjecMEM: Memory Injection Attack on LLM Agent Memory Systems
[Kryptografia i bezpieczeństwo] Autorzy: Hanling Tian, Gengyu Zhang, Zeyang Sha i 5 więcej
Memory is becoming a default subsystem in deployed LLM agents to provide persistent personalization and continuity. This naturally prompts a question: will memory system introduce new vulnerabilities into agents? Thus we propose InjecMEM, a novel memory injection attack paradigm that requires only a single interaction (no read/edit access to memory store) to steer later responses of related queries toward a pre-specified output. Guided by the retrieval-then-generate mechanism of memory systems, we craft the injection with a retriever-agnostic anchor and an adversarial command. The anchor contains high-recall topical cues so that downstream retrieval consistently associates the record with the target topic. The command is a short sequence optimized to remain effective under uncertain fused contexts, variable placements, and long prompts so that it reliably steers outputs once retrieved. …
- Kategoria arxiv
- cs.CR
- Kategoria
- Kryptografia i bezpieczeństwo