MIR第4期专题"Security and Ethics of Generative Artificial Intelligence"已于8月正式出版，12篇特约好文，欢迎阅读！

Special Issue  Vol. 23, No.4

专题客座编委：

董晶, 中国科学院自动化研究所, 中国

Matteo Ferrara, University of Bologna, Italy

赫然, 中国科学院自动化研究所, 中国

Tao Dacheng, Nanyang Technological University, Singapore

Philip H. S. Torr, University of Oxford, UK

Rama Chellappa, Johns Hopkins University, USA

专题 · Editorial

Editorial for Special Issue on Security and Ethics of Generative Artificial Intelligence

Jing Dong, Matteo Ferrara, Ran He, Dacheng Tao, Philip H. S. Torr & Rama Chellappa

https://link.springer.com/article/10.1007/s11633-026-1677-2

https://www.mi-research.net/article/doi/10.1007/s11633-026-1677-2

专题 · 综述

Embodied Intelligence Security with Vision-language Models: A Survey

Junxian Duan, Haisu Zhu, Canhui Liu, Shiyi Li, Xiangyun Tang & Yingxue Wang

https://link.springer.com/article/10.1007/s11633-025-1626-x

https://www.mi-research.net/article/doi/10.1007/s11633-025-1626-x

专题 · 研究论文

The Latent Seal: Robust Model Watermarking for Latent Diffusion Model

Qin Zhao, Tong Liu, Xiaochen Yuan, Guoheng Huang, Xueyuan Gong & Wei Wang

https://link.springer.com/article/10.1007/s11633-025-1620-y

https://www.mi-research.net/article/doi/10.1007/s11633-025-1620-y

专题 · 研究论文

GaussianSeal: Rooting Adaptive Watermarks for 3D Gaussian Generation Model

Runyi Li, Xuanyu Zhang, Chuhan Tong, Zhipei Xu & Jian Zhang

https://link.springer.com/article/10.1007/s11633-025-1588-7

https://www.mi-research.net/article/doi/10.1007/s11633-025-1588-7

专题 · 研究论文

T2IW: Joint Text to Image & Watermark Generation

Guokai Zhang, Yuting Su, Lanjun Wang, Guochang Liu, Dan Song & An-An Liu

https://link.springer.com/article/10.1007/s11633-025-1606-9

https://www.mi-research.net/article/doi/10.1007/s11633-025-1606-9

专题 · 研究论文

Visual Adversarial Attack on Vision-language Models for Autonomous Driving

Tianyuan Zhang, Lu Wang, Xinwei Zhang, Yitong Zhang, Boyi Jia, Siyuan Liang, Shengshan Hu, Qiang Fu, Aishan Liu & Xianglong Liu

https://link.springer.com/article/10.1007/s11633-026-1667-4

https://www.mi-research.net/article/doi/10.1007/s11633-026-1667-4

专题 · 研究论文

Adversarial Patches in 3D: A Stealth Threat to Monocular Depth Estimation

Meng Pan, Yunshu Dai, Jianhuang Lai & Xiaohua Xie

https://link.springer.com/article/10.1007/s11633-025-1617-6

https://www.mi-research.net/article/doi/10.1007/s11633-025-1617-6

专题 · 研究论文

GTCP: A General Traces Compensation Purifier for Enhancing the Adversarial Robustness of Deepfake Detection

Yu Chen, Yang Yu, Rui Zhai, Rongrong Ni, Haoliang Li, Wei Wang & Yao Zhao

https://link.springer.com/article/10.1007/s11633-025-1616-7

https://www.mi-research.net/article/doi/10.1007/s11633-025-1616-7

专题 · 研究论文

Towards Understanding the Cognitive Habits of Large Reasoning Models

Jianshuo Dong, Yujia Fu, Chuanrui Hu, Chao Zhang & Han Qiu

https://link.springer.com/article/10.1007/s11633-026-1654-9

https://www.mi-research.net/article/doi/10.1007/s11633-026-1654-9

专题 · 研究论文

Reasoning-targeted Jailbreak Attacks on Large Reasoning Models via Semantic Triggers and Psychological Framing

Zehao Wang & Lanjun Wang

https://link.springer.com/article/10.1007/s11633-025-1602-0

https://www.mi-research.net/article/doi/10.1007/s11633-025-1602-0

专题 · 研究论文

Reformulation is All You Need: Addressing Malicious Textual Features in DNNs

Yi Jiang, Oubo Ma, Yong Yang, Tong Zhang & Shouling Ji

https://link.springer.com/article/10.1007/s11633-025-1594-9

https://www.mi-research.net/article/doi/10.1007/s11633-025-1594-9

专题 · 研究论文

Countering Adversarial Attacks with Multimodal Image Fusion

Dong Yu, Chunjie Zhang, Xiaoyu Zhang, Gaopeng Zhang & Yao Zhao

https://link.springer.com/article/10.1007/s11633-025-1613-x

https://www.mi-research.net/article/doi/10.1007/s11633-025-1613-x

MIR为所有读者提供免费寄送纸刊服务，如您对本篇文章感兴趣，请点击下方链接填写收件地址，编辑部将尽快为您免费寄送纸版全文！

说明：如遇特殊原因无法寄达的，将推迟邮寄时间，咨询电话010-82544737

收件信息登记：

https://lcn76mgd97vz.feishu.cn/share/base/form/shrcnsQ6cmRjqoxPF5WDowSBFVr

关于Machine Intelligence Research

Machine Intelligence Research（简称MIR）由中国科学院自动化研究所主办，于2022年正式出版。MIR立足国内、面向全球，着眼于服务国家战略需求，刊发机器智能领域最新原创研究性论文、综述、评论等，全面报道国际机器智能领域的基础理论和前沿创新研究成果，促进国际学术交流与学科发展，服务国家人工智能科技进步。期刊入选"中国科技期刊卓越行动计划"，已被ESCI、EI、Scopus、中国科技核心期刊、CSCD等20余家国际数据库收录，入选图像图形领域期刊分级目录-T2级知名期刊。2022年首个CiteScore分值在计算机科学、工程、数学三大领域的八个子方向排名均跻身Q1区，最佳排名挺进Top 4%，2023年CiteScore分值继续跻身Q1区。2024年获得首个影响因子(IF) 6.4，位列人工智能及自动化&控制系统两个领域JCR Q1区；2026年发布的最新影响因子达10.0，继续跻身JCR Q1区，最佳排名进入全球第5名；2026年进入期刊分区表1区，最新CiteScore分值达17.8。

支持单位：