A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle
arXiv:2604.16548v5 Announce Type: replace-cross Abstract: The emergence of writable, cross-session persistent memory in LLM agents introduces a qualitatively different threat landscape from conventional input-centric security concerns, characterized by three properties: persistence, statefulness, and propagation. To systematically characterize this landscape, we propose a Memory Lifecycle Framework that organizes attacks, defenses, and their cross-phase dependencies along two axes: six lifecycle phases (Write, Store, Retrieve, Execute, Share & Propagate, Forget & Rollback) and four security objectives (Integrity, Confidentiality, Availability, Governance). This analysis in turn exposes the need for explicit security requirements at the system level, motivating Verifiable Memory Governance (VMG), a framework of five architectural primitives for specifying and evaluating auditable, recoverable control over memory state within declared system and threat-model boundaries. Our analysis motivates integrating provenance, versioning, and policy-aware retention with retrieval and execution defenses to support auditable prevention, containment, and recovery across the lifecycle.
Get stories like this every Monday
The week's most important AI news in one email. Free, unsubscribe anytime.
Score: 2.75
Engagement proxy: 0
Canonical link: https://arxiv.org/abs/2604.16548