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。

2025-07-30 至 2025-07-30 共收录 16 信号源:cs.CL, cs.AI, cs.CY, cs.LG

1. 安全评测 16 篇

2501.13818 2025-07-30 cs.AI cs.CV cs.LG 87%

Ensuring Medical AI Safety: Interpretability-Driven Detection and Mitigation of Spurious Model Behavior and Associated Data

Frederik Pahde, Thomas Wiegand, Sebastian Lapuschkin, Wojciech Samek

机构 * Fraunhofer Heinrich Hertz Institut(弗劳恩霍夫 Heinrich Hertz 研究所) Technische Universität Berlin(柏林技术大学) Berlin Institute for the Foundations of Learning and Data (BIFOLD)(柏林学习与数据基础研究所(BIFOLD))

专题命中 安全评测 :safety(title,abstract);AI safety(title);分类 cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.21169 2025-07-30 cs.CY cs.AI 84%

Trustworthy AI: UK Air Traffic Control Revisited

Rob Procter, Mark Rouncefield

专题命中 安全评测 :trustworthy(title,abstract);safety(abstract);分类 cs.AI、cs.CY

Comments 6 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.21637 2025-07-30 cs.AI 83%

Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models

Wanying Wang, Zeyu Ma, Han Zheng, Xin Tan, Mingang Chen

机构 * Shanghai Key Laboratory of Computer Software Testing and Evaluating(上海软件测试与评估 key laboratory) Shanghai Normal University(上海Normal University) TrustAI Pte. Ltd. East China Normal University(东华师范大学)

专题命中 安全评测 :safety(title,abstract);alignment(abstract);分类 cs.AI

Comments Accepted by ACM Multimedia 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.21782 2025-07-30 cs.CL 79%

The Problem with Safety Classification is not just the Models

Sowmya Vajjala

专题命中 安全评测 :safety(title,abstract);分类 cs.CL

Comments Pre-print, Short paper

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.21741 2025-07-30 cs.CV cs.MM 78%

MAGE: Multimodal Alignment and Generation Enhancement via Bridging Visual and Semantic Spaces

Shaojun E, Yuchen Yang, Jiaheng Wu, Yan Zhang, Tiejun Zhao, Ziyan Chen

机构 * Global Tone Communication Technology Co., Ltd.(全球 tone 通信技术有限公司) Faculty of computing, Harbin Institute of Technology(哈尔滨工业大学计算机学院) School of Computer Science and Technology, Beijing Jiaotong University(北京交通大学计算机科学与技术学院)

专题命中 安全评测 :alignment(title,abstract)

Comments 9 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.21145 2025-07-30 cs.CR 78%

Leveraging Trustworthy AI for Automotive Security in Multi-Domain Operations: Towards a Responsive Human-AI Multi-Domain Task Force for Cyber Social Security

Vita Santa Barletta, Danilo Caivano, Gabriel Cellammare, Samuele del Vescovo, Annita Larissa Sciacovelli

专题命中 安全评测 :trustworthy(title,abstract)

Comments 13 pages, 6 figures, 1 table

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.22034 2025-07-30 cs.AI cs.CL cs.LG 67%

UserBench: An Interactive Gym Environment for User-Centric Agents

Cheng Qian, Zuxin Liu, Akshara Prabhakar, Zhiwei Liu, Jianguo Zhang, Haolin Chen, Heng Ji, Weiran Yao, Shelby Heinecke, Silvio Savarese, Caiming Xiong, Huan Wang

机构 * Salesforce AI Research(Salesforce AI研究部) University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

专题命中 安全评测 :alignment(abstract);分类 cs.CL、cs.AI、cs.LG

Comments 25 Pages, 17 Figures, 6 Tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.21815 2025-07-30 cs.CL cs.CY 62%

HRIPBench: Benchmarking LLMs in Harm Reduction Information Provision to Support People Who Use Drugs

Kaixuan Wang, Chenxin Diao, Jason T. Jacques, Zhongliang Guo, Shuai Zhao

机构 * University of St. Andrews(圣安德鲁大学) University of Edinburgh(爱丁堡大学) Nanyang Technological University(南洋理工大学)

专题命中 安全评测 :safety(abstract);分类 cs.CL、cs.CY

Comments 15 pages, 5 figures, 12 tables, a dataset

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.21504 2025-07-30 cs.LG cs.AI 62%

Evaluation and Benchmarking of LLM Agents: A Survey

Mahmoud Mohammadi, Yipeng Li, Jane Lo, Wendy Yip

机构 * SAP Labs(SAP实验室)

专题命中 安全评测 :safety(abstract);分类 cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.21340 2025-07-30 cs.CL cs.AI cs.DB cs.IR 62%

StructText: A Synthetic Table-to-Text Approach for Benchmark Generation with Multi-Dimensional Evaluation

Satyananda Kashyap, Sola Shirai, Nandana Mihindukulasooriya, Horst Samulowitz

机构 * IBM Research(IBM研究院)

专题命中 安全评测 :alignment(abstract);分类 cs.CL、cs.AI

Comments Data available: https://huggingface.co/datasets/ibm-research/struct-text and code available at: https://github.com/ibm/struct-text

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.21188 2025-07-30 cs.LG cs.AI 62%

Embeddings to Diagnosis: Latent Fragility under Agentic Perturbations in Clinical LLMs

Raj Krishnan Vijayaraj

机构 * Independent Researcher(独立研究者)

专题命中 安全评测 :safety(abstract);分类 cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2306.06123 2025-07-30 cs.CR cs.AI cs.CV cs.LG 62%

Adversarial attacks and defenses in explainable artificial intelligence: A survey

Hubert Baniecki, Przemyslaw Biecek

机构 * University of Warsaw(华沙大学) Warsaw University of Technology(华沙理工大学)

专题命中 安全评测 :safety(abstract);分类 cs.AI、cs.LG

Comments Accepted by Information Fusion

Journal ref Information Fusion, vol. 107, 102303, 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.21488 2025-07-30 cs.AI 57%

Learning to Imitate with Less: Efficient Individual Behavior Modeling in Chess

Zhenwei Tang, Difan Jiao, Eric Xue, Reid McIlroy-Young, Jon Kleinberg, Siddhartha Sen, Ashton Anderson

机构 * University of Toronto(多伦多大学) Harvard University(哈佛大学) Cornell University(康奈尔大学) Microsoft Research(微软研究院)

专题命中 安全评测 :alignment(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.21076 2025-07-30 cs.CY 57%

Making a Case for Research Collaboration Between Artificial Intelligence and Operations Research Experts

Radhika Kulkarni, Gianluca Brero, Yu Ding, Swati Gupta, Sven Koenig, Ramayya Krishnan, Thiago Serra, Phebe Vayanos, Segev Wasserkrug, Holly Wiberg

专题命中 安全评测 :trustworthy(abstract);分类 cs.CY

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.03274 2025-07-30 cs.AI 57%

A Scalable Approach to Probabilistic Neuro-Symbolic Robustness Verification

Vasileios Manginas, Nikolaos Manginas, Edward Stevinson, Sherwin Varghese, Nikos Katzouris, Georgios Paliouras, Alessio Lomuscio

机构 * Department of Computer Science and Leuven.AI KU Leuven Belgium(比利时列日大学计算机科学系) Department of Computing Imperial College London UK(伦敦帝国学院计算机系)

专题命中 安全评测 :safety(abstract);分类 cs.AI

Comments 19th Conference on Neurosymbolic Learning and Reasoning

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.21157 2025-07-30 cs.CR cs.CV 50%

Unmasking Synthetic Realities in Generative AI: A Comprehensive Review of Adversarially Robust Deepfake Detection Systems

Naseem Khan, Tuan Nguyen, Amine Bermak, Issa Khalil

机构 * Department of Computer Science(计算机科学系) Hamad bin Khalifa University(哈马德·本·哈利法大学) Qatar Computing Research Institute(卡塔尔计算研究所)

专题命中 安全评测 :trustworthy(abstract)

Comments 27 pages, 4 Tables, 3 Figures

详情

展开后加载摘要…

URL PDF HTML 收藏