作者位次 #4/4ICLR 2026Poster· Social Aspects / Privacy-preserving Statistics and Machine Learning
WARP: Weight Teleportation for Attack-Resilient Unlearning Protocols
Mohammad M Maheri · Xavier Cadet · Peter Chin · Hamed Haddadi
首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。
实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。
Mohammad M Maheri · Xavier Cadet · Peter Chin · Hamed Haddadi
Zhonghao Zhan · Huichi Zhou · Zhenhao Li · Peiyuan Jing · Krinos Li · Hamed Haddadi
Tool-integrated agents are deployed on the premise that external tools ground their outputs in reality. Yet this very reliance creates a critical attack surface. Current evaluations benchmark capability in benign settings, asking “can the agent use tools correctly” but never “what if the tools li...