Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents

본문 미리보기

arXiv:2607.23444v1 Announce Type: new Abstract: LLM-based agents extend large language models with long-term memory (LTM) that persists privacy-sensitive user data across sessions. Production systems mitigate extraction risks through memory isolation, binding each user's LTM to a unique identifier. This defense has blocked known attacks on shared storage, fostering the assumption that isolated LTM is secure. We identify the tool interface as an overlooked attack surface. Agents routinely embed