Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers

v1v2 (latest)

Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers

18 June 2025

ArXiv (abs)PDF HTML Github (13★)

Papers citing "Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers"

4 / 4 papers shown

Title
Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards Aaron Tu Weihao Xuan Heli Qi X. Y. Huang Qingcheng Zeng ... Amin Saberi Naoto Yokoya Jure Leskovec Yejin Choi Fang Wu OffRL 8 0 0 26 Sep 2025
Beyond Data Privacy: New Privacy Risks for Large Language Models Yuntao Du Zitao Li Ninghui Li Bolin Ding PILM ELM 92 0 0 16 Sep 2025
A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models Yanbo Wang Yongcan Yu Jian Liang Ran He HILM LRM 87 2 0 04 Sep 2025
Does More Inference-Time Compute Really Help Robustness? Tong Wu Chong Xiang Jiachen T. Wang Weichen Yu Chawin Sitawarin Vikash Sehwag Prateek Mittal AAML LRM 79 2 0 21 Jul 2025