教育经历：

2009-09 至 2014-06, 中国科学院自动化研究所, 模式识别与智能系统, 博士

2011-09 至 2013-09, 美国伦斯勒理工学院, 计算机视觉, 其他

2005-09 至 2009-06, 北京科技大学, 自动化, 学士

工作经历：

 2025-09 – 至今, 香港中文大学（深圳）,人工智能学院, 副教授

2020-09 – 2025/09, 香港中文大学（深圳）, 数据科学学院, 副教授

2016-11 至 2020-08, 腾讯人工智能实验室, 计算机视觉中心, 专家研究员

2014-08 至 2016-11, 沙特阿卜杜拉国王科技大学（KAUST），博士后

吴保元博士现任香港中文大学（深圳）人工智能学院终身副教授、助理院长（科研）、深圳河套学院双聘教授。其研究方向包括可信人工智能、机器学习和计算机视觉，在人工智能的顶级期刊和会议上发表论文120余篇，其中包括权威期刊TPAMI、IJCV 15篇，谷歌学术引用12000余次。其担任人工智能领域国际期刊IEEE TIFS高级领域编委、第五届中国模式识别与计算机视觉大会PRCV 2022组委会主席、国际顶级学术会议CVPR、NeurIPS、ICLR、ICML、AAAI领域主席、中国自动化学会模式识别与机器智能专委会副秘书长，连续多年入选斯坦福大学“全球前2%顶尖科学家”榜单。作为项目负责人承担科技部重点研发计划重点专项课题、广东省杰青、广东省科技创新青年拔尖人才、国家自然科学基金面上等多项课题，并与腾讯、华为、快手等知名企业建立长期科研合作。荣获2023年度香港中文大学（深圳）青年科研奖。

[1]Wu, Baoyuan; Ghanem, Bernard. “Lp-Box ADMM: A Versatile Framework for Integer Programming.” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2019, 41(7): 1695–1708. (CCF-A类，共同第一作者和唯一通讯作者)

[2]Wu, Baoyuan(corresponding author); Zhu, Mingli; Zheng, Meixi; Zhu, Zihao; Wei, Shaokui; Zhang, Mingda; Chen, Hongrui; Yuan, Danni; Liu, Li; Liu, Qingshan. “Defenses in Adversarial Machine Learning: A Systematic Survey from the Lifecycle Perspective.” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025. (CCF-A类，唯一通讯作者)

[3] Wang, Ruotong; Chen, Hongrui; Zhu, Zihao; Liu, Li; Wu, Baoyuan (corresponding author). “Versatile Backdoor Attack with Visible, Semantic, Sample-specific and Compatible Triggers.” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025. (CCF-A类，唯一通讯作者)

[4] Zheng, Meixi; Yan, Xuanchen; Zhu, Zihao; Chen, Hongrui;Wu, Baoyuan(corresponding author). “BlackboxBench: A Comprehensive Benchmark of Black-box Adversarial Attacks.” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025. (CCF-A类，唯一通讯作者)

[5]Wu, Baoyuan; Zhu, Zihao; Liu, Li; Liu, Qingshan; He, Zhaofeng; Lyu, Siwei. “Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspective.” International Journal of Computer Vision (IJCV), 2025. (CCF-A类，唯一第一作者和唯一通讯作者)

[6]Wu, Baoyuan; Chen, Hongrui; Zhang, Mingda; Zhu, Zihao; Wei, Shaokui; Yuan, Danni; Zhu, Mingli; Wang, Ruotong; Liu, Li; Shen, Chao. “BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning.” International Journal of Computer Vision (IJCV), 2025. (CCF-A类，唯一第一作者和唯一通讯作者)

[7] Yin, Fei; Zhang, Yong; Wu, Baoyuan; Feng,Yan; Zhang, Jingyi; Fan,Yanbo；Yang， Yujiu. “Generalizable Black-Box Adversarial Attack with Meta Learning.”IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024, 46(3): 1804–1818. (CCF-A类，共同第一作者和共同通讯作者)

[8] Song, Chuanbiao; Fan, Yanbo; Zhou, Aoyang; Wu, Baoyuan; Li, Yiming; Li, Zhifeng; He, Kun. Regional Adversarial Training for Better Robust Generalization. International Journal of Computer Vision (IJCV), 2024. (CCF-A类，共同通讯作者)

[9] Bai, Jiawang; Wu, Baoyuan; Li, Zhifeng; Xia, Shu-Tao. Versatile Weight Attack via Flipping Limited Bits. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023, 45(11), 13653–13665. (CCF-A类，共同通讯作者)

[10]Wu, Baoyuan; Shen, Li; Ghanem, Bernard; Zhang, Tong. “MAP Inference via L2-Sphere Linear Program Reformulation.” International Journal of Computer Vision (IJCV), 2020, 128: 1913–1936. (CCF-A类，唯一第一作者)

[11]Wu, Baoyuan; Jia, Fan; Liu, Wei; Ghanem, Bernard; Lyu, Siwei. “Multi-label learning with missing labels using mixed dependency graphs.” International Journal of Computer Vision (IJCV), 2018, 126(8): 875--896. (CCF-A类，唯一第一作者和唯一通讯作者)