Memory Sandbox at the memory layer reduces persistent memory attack success rate to 0% for eight of nine models with no utility cost, while input-level and retrieval-level defenses achieve near-baseline attack success rates of 88-89%.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Defense effectiveness across architectural layers: a mechanistic evaluation of persistent memory attacks on stateful LLM agents
Memory Sandbox at the memory layer reduces persistent memory attack success rate to 0% for eight of nine models with no utility cost, while input-level and retrieval-level defenses achieve near-baseline attack success rates of 88-89%.