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。

2025-09-01 至 2025-09-01 共收录 2 篇信号源：cs.CL, cs.AI, cs.CY, cs.LG

1. 隐私与版权 2 篇

2508.21815 2025-09-01 cs.LG 57%

Achieving Hilbert-Schmidt Independence Under Rényi Differential Privacy for Fair and Private Data Generation

Tobias Hyrup, Emmanouil Panagiotou, Arjun Roy, Arthur Zimek, Eirini Ntoutsi, Peter Schneider-Kamp

机构 * Department of Mathematics and Computer Science University of Southern Denmark（丹麦南部大学数学与计算机科学系）； Department of Mathematics and Computer Science Freie Universität Berlin（柏林自由大学数学与计算机科学系）； Faculty for Informatik Universität der Bundeswehr München（联邦国防军大学慕尼黑信息学院）

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

2505.12490 2025-09-01 cs.CR 50%

Improving Google A2A Protocol: Protecting Sensitive Data and Mitigating Unintended Harms in Multi-Agent Systems

Yedidel Louck, Ariel Stulman, Amit Dvir

专题命中隐私与版权：prompt injection(abstract)