From Attack Success to Attack Severity: Counterfactual Memory Attacks on LLM Agents
As LLM agents increasingly rely on persistent memory for long-horizon and personalized behavior, they can retain and reuse information across interactions, but this also creates a lasting channel through which malicious memory writes can influence future behavior. Persistent-memory attacks are typically evaluated by wh...
Ming-Xi Zou, Lang-Zhang Liang, Zhuo Wang et al.
· 0 citations