arXivZhewen Tan, Yilun Yao, Huiyan Jin, Wenhan Yu, Guoan Wang, Mengyuan Fan, liang lu, Feng Liu, Xiangzheng Zhang, Duohe Ma, Tong Yang, Lin SunFri, May 22, 2026, 8:03 AM PDT
score 14.6
Framework detects poisoned memories in AI agents after attacks occur
Original: MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly Detection
Source: arxiv.org ↗
Writing ELI5 summary…