#artificial intelligence
Sep 2026
From Attack Success to Attack Severity: Counterfactual Memory Attacks on LLM Agents
MemHarm is introduced, which predeclares a finite class of sparse, grounded semantic edits, evaluates candidates through the normal agent memory interface using offline paired-loss feedback, and certifies resolved selections within that class of sparse, grounded semantic edits.
Ming-Xi Zou, Lang-Zhang Liang, Zhuo Wang et al.
· arXiv.org · 1 citation