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。

2025-09-29 至 2025-09-29 共收录 3 篇信号源：cs.CL, cs.AI, cs.CY, cs.LG

1. 隐私与版权 3 篇

2509.21695 2025-09-29 cs.LG 74%

Wav2Arrest 2.0: Long-Horizon Cardiac Arrest Prediction with Time-to-Event Modeling, Identity-Invariance, and Pseudo-Lab Alignment

Saurabh Kataria, Davood Fattahi, Minxiao Wang, Ran Xiao, Matthew Clark, Timothy Ruchti, Mark Mai, Xiao Hu

机构 * Nell Hodgson Woodruff School of Nursing, Emory University（埃默里大学护理学院）； Department of Pediatrics, Emory School of Medicine（埃默里医学院儿科部）

专题命中隐私与版权：alignment(title)；分类 cs.LG

Comments Submitted to BPSC

2406.00276 2025-09-29 cs.LG cs.AI cs.CE physics.data-an 62%

Machine Learning-Assisted Sustainable Remanufacturing, Reusing and Recycling for Lithium-ion Batteries

Shengyu Tao

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

Comments This is a PhD thesis from Dr. Shengyu Tao at Tinsghua University and University of California at Berkeley

2509.21712 2025-09-29 cs.CR cs.AI 57%

Not My Agent, Not My Boundary? Elicitation of Personal Privacy Boundaries in AI-Delegated Information Sharing

Bingcan Guo, Eryue Xu, Zhiping Zhang, Tianshi Li

机构 * Department of Human Centered Design & Engineering, University of Washington（华盛顿大学人中心设计与工程系）； School of Information Sciences, University of Illinois（伊利诺伊大学香槟分校信息科学学院）； Khoury College of Computer Sciences, Northeastern University（东北大学计算机科学学院）

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