arXivDaily arXiv每日学术速递 周一至周五更新

AI 大模型

大模型对齐与安全

大模型对齐、安全、越狱、红队、提示注入和可信评测。

2025-10-22 至 2025-10-22 共收录 2 信号源:cs.CL, cs.AI, cs.CY, cs.LG

1. 隐私与版权 2 篇

2510.18674 2025-10-22 cs.CR cs.AI 57%

Exploring Membership Inference Vulnerabilities in Clinical Large Language Models

Alexander Nemecek, Zebin Yun, Zahra Rahmani, Yaniv Harel, Vipin Chaudhary, Mahmood Sharif, Erman Ayday

机构 * Case Western Reserve University(凯斯西储大学) Tel Aviv University(特拉维夫大学)

专题命中 隐私与版权 :alignment(abstract);分类 cs.AI

Comments Accepted at the 1st IEEE Workshop on Healthcare and Medical Device Security, Privacy, Resilience, and Trust (IEEE HMD-SPiRiT)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.18493 2025-10-22 cs.CR cs.AI cs.HC 57%

One Size Fits All? A Modular Adaptive Sanitization Kit (MASK) for Customizable Privacy-Preserving Phone Scam Detection

Kangzhong Wang, Zitong Shen, Youqian Zhang, Michael MK Cheung, Xiapu Luo, Grace Ngai, Eugene Yujun Fu

机构 * The Hong Kong Polytechnic University(香港理工大学) The Education University of Hong Kong(香港教育大学)

专题命中 隐私与版权 :safety(abstract);分类 cs.AI

Comments 9 pages

详情

展开后加载摘要…

URL PDF HTML 收藏