arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

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。

2025-10-10 至 2025-10-10 共收录 67 信号源:cs.CL, cs.AI, cs.CY, cs.LG

1. 其他安全 10 篇

2510.08464 2025-10-10 cs.RO cs.LG 57%

Don't Run with Scissors: Pruning Breaks VLA Models but They Can Be Recovered

Jason Jabbour, Dong-Ki Kim, Max Smith, Jay Patrikar, Radhika Ghosal, Youhui Wang, Ali Agha, Vijay Janapa Reddi, Shayegan Omidshafiei

专题命中 其他安全 :safety(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.08385 2025-10-10 cs.CV cs.AI cs.DB cs.IR 57%

Detecting Legend Items on Historical Maps Using GPT-4o with In-Context Learning

Sofia Kirsanova, Yao-Yi Chiang, Weiwei Duan

机构 * University of Minnesota(明尼苏达大学) Inferlink Corporation(Inferlink公司)

专题命中 其他安全 :alignment(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.08381 2025-10-10 cs.RO cs.AI 57%

Airy: Reading Robot Intent through Height and Sky

Baoyang Chen, Xian Xu, Huamin Qu

机构 * Hong Kong University of Science and Technology(香港理工大学) Central Academy of Fine Arts(中央美术学院) Lingnan University(岭南大学)

专题命中 其他安全 :safety(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.18344 2025-10-10 cs.CL 57%

Speculate Deep and Accurate: Lossless and Training-Free Acceleration for Offloaded LLMs via Substitute Speculative Decoding

Pei-Shuo Wang, Jian-Jia Chen, Chun-Che Yang, Chi-Chih Chang, Ning-Chi Huang, Mohamed S. Abdelfattah, Kai-Chiang Wu

专题命中 其他安全 :alignment(abstract);分类 cs.CL

Comments Accepted by NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.16592 2025-10-10 cs.CL cs.MM 57%

What Media Frames Reveal About Stance: A Dataset and Study about Memes in Climate Change Discourse

Shijia Zhou, Siyao Peng, Simon M. Luebke, Jörg Haßler, Mario Haim, Saif M. Mohammad, Barbara Plank

机构 * MaiNLP & MCML, LMU Munich, Germany(LMU慕尼黑媒体与传播系) Department of Media and Communication, LMU Munich, Germany(LMU慕尼黑媒体与传播系) National Research Council Canada, Ottawa, Canada(加拿大国家研究委员会)

专题命中 其他安全 :alignment(abstract);分类 cs.CL

Comments 20 pages, 9 figures, EMNLP Findings

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.08496 2025-10-10 cs.CR 50%

AI-Driven Post-Quantum Cryptography for Cyber-Resilient V2X Communication in Transportation Cyber-Physical Systems

Akid Abrar, Sagar Dasgupta, Mizanur Rahman, Ahmad Alsharif

专题命中 其他安全 :safety(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.07941 2025-10-10 cs.SE 50%

An AUTOSAR-Aligned Architectural Study of Vulnerabilities in Automotive SoC Software

Srijita Basu, Haraldsson Bengt, Miroslaw Staron, Christian Berger, Jennifer Horkoff, Magnus Almgren

专题命中 其他安全 :safety(abstract)

Comments 16 pages, 7 figures, 18th International Conference on the Quality of Information and Communications Technology

详情

展开后加载摘要…

URL PDF HTML 收藏