一作ICLR 2026Poster· Social Aspects / Privacy-preserving Statistics and Machine Learning
Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs
Dong Yan · Jian Liang · Ran He · Tieniu Tan
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。
Dong Yan · Jian Liang · Ran He · Tieniu Tan
Dong Yan · Jian Liang · Yanbo Wang · Shuo Lu · Ran He · Tieniu Tan
Test-Time Reinforcement Learning (TTRL) enables Large Language Models (LLMs) to enhance reasoning capabilities on unlabeled test streams by deriving pseudo-rewards from majority voting consensus.However, existing TTRL methods rely exclusively on positive pseudo-labeling strategies.Such reliance b...