Biography

I am a tenure-track Associate Professor in the School of Intelligence Science and Technology, Nanjing University (Suzhou Campus), at the NJU-PR group led by Prof. Caifeng Shan and Prof. Tieniu Tan.  I work on cutting-edge research in Trustworthy and Generative AI. Previously, I was a Senior Research Scientist at Ant Research (Oct. 2023 to Jun. 2025) and a Senior Research Scientist at Tencent AI Lab (Jul. 2018 to Oct. 2023), where I primarily led research teams in conducting cutting-edge research explorations in AI security and multimodal visual content generation. From 2013 to 2018, I earned my PhD degree from the National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), supervised by Prof. Bao-Gang Hu and Prof. Ran He. My doctoral research focused on fundamental problems in machine learning. From 2016 to 2017, I spent a wonderful year as a visiting student at the Computer Vision and Machine Learning Lab (CVML) at the University at Albany, State University of New York, supervised by Prof. Siwei Lyu. I received my BS degree from Hunan University in June 2013, majoring in Computer Science and Technology.

My research focuses on Trustworthy and Generative AI:

• Trustworthy AI: We study secure and controllable artificial intelligence technologies. We currently focus on addressing critical security challenges in Multimodal Large Language Models (MLLMs)/Agents and the security challenges of AI-generated content (AIGC), including jailbreaking/adversarial/backdoor attacks and defenses, and the copyright protection and AI detection for generated content. Some of my research works around Trustworthy AI are RAT(IJCV24), ATAS(TIP23), RAP (NeurIPS22), SAGB (NeurIPS22), CGAttack(CVPR22), RND(NeurIPS21), SAPF(ECCV20). 

• Generative AI: We study human-centric (face/body) multimodal content generation, including digital avatar animation techniques, where our goal is to develop 2D/3D digital avatars with multimodal perception (vision, audio, and environments) and interactive capabilities, enabling autonomous (interactive) action generation—both among avatars and between avatars and their surroundings; we are also interested in broad topics in multimodal image and video generation and editings. Some of my research works around human-centric generation/editing are Echo(Siggraph Asia 2025), DualTalk(CVPR25), DiffListener(CVPR25), DGTalker(ICCV25), P3G(ECCV24), NOFA(Siggraph23), HFA-GP(CVPR23), HFGA(CVPR22).

课题组长期招收优秀的同学加入

• 招收2026年入学博士（普博，2名），感兴趣的同学欢迎联系！详细介绍请移步【硕博招生说明】对每一位学生将提供1v1的科研指导，对于表现优秀的学生积极推荐大厂实习机会等

• 每年固定招收硕士、博士，欢迎有意申请2027年及以后入学的硕士、博士提前联系，合适的同学会提供远程/线下科研合作指导

• 课题组长期欢迎优秀本科生提前进组科研，将提供1v1科研指导和实验环境

• 请邮件联系 fanyanbo0124@gmail.com或yanbofan@nju.edu.cn，请附上个人简历、论文/竞赛/研究计划（如有），谢谢！

News

• 2025/08/15 -- I'm invited as an Area Chair of ICLR 2026.

• 2025/08/11 -- One paper about Digital Avatar is conditionally accepted to Siggraph Asia 2025.

• 2025/06/26 -- Two papers about Digital Avatar are accepted to ICCV 2025.

• I will join Nanjing University in July 2025.

• 2025/02/27 -- Five papers about Digital Avatar are accepted to CVPR 2025.

• 2024/12/18 -- I will serve as an Area Chair of ICME 2025.

• 2024/10/07 -- One paper about adversarial examples is accepted to Pattern Recognition.

• 2024/08/20 -- I'm invited as an Area Chair of ICLR 2025.

• 2024/07/14 -- I'm invited as an Area Chair of WACV 2025.

• 2024/07/02 -- One paper about text-to-texture is accepted to ECCV 2024.

• 2024/04/25 -- One paper about adversarial training is accepted to IJCV.

• 2023/09/22 -- One paper about motion generation is accepted to NeurIPS 2023.

• 2023/08/15 -- One paper about Fast Adversarial Training is accepted to TIP.

Selected Publications

#corresponding author, *co-first authors

1. Echo: Enhancing Conversational Behavior Generation via Hierarchical Semantic Comprehension with Large Language Models
   Haiwei Xue, Yanbo Fan#, Xuan Wang, Zhiyong Wu
   [Siggraph Asia 2025, conference track]

2. DGTalker: Disentangled Generative Latent Space Learning for Audio-Driven Gaussian Talking Heads
   Xiaoxi Liang, Yanbo Fan#, Qiya Yang, Xuan Wang, Wei Gao, Ge Li
   [ICCV 2025]

3. DualTalk: Dual-Speaker Interaction for 3D Talking Head Conversations
   Ziqiao Peng, Yanbo Fan#, Haoyu Wu, Xuan Wang, Hongyan Liu, Jun He, Zhaoxin Fan
   [CVPR 2025]

4. Diffusion-based Realistic Listening Head Generation via Hybrid Motion Modeling
   Yinuo Wang, Yanbo Fan#, Xuan Wang, Yu Guo, Fei Wang
   [CVPR 2025, Highlight]

5. Understanding Adversarial Robustness Against On-manifold Adversarial Examples.
   Jiancong Xiao, Liusha Yang, Yanbo Fan#, Jue Wang, Zhi-Quan Luo
   [Pattern Recognition 2024]

6. Learning Pseudo 3D Guidance for View-consistent Texturing with 2D Diffusion
   Kehan Li, Yanbo Fan#, Yang Wu, Zhongqian Sun, Wei Yang, Xiangyang Ji, Li Yuan, Jie Chen.
   [ECCV 2024]

7. Regional Adversarial Training for Better Robust Generalization
   Chuanbiao Song*, Yanbo Fan*, Aoyang Zhou*, Baoyuan Wu, Yiming Li, Zhifeng Li, Kun He
   [International Journal of Computer Vision, IJCV 2024]

8. UCF: Uncovering Common Features for Generalizable Deepfake Detection
   Zhiyuan Yan, Yong Zhang, Yanbo Fan, Baoyuan Wu
   [ICCV 2023]

9. Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs
   Peng Jin, Yang Wu, Yanbo Fan, Zhongqian Sun, Yang Wei, Li Yuan
   [NeurIPS 2023]

10. Fast adversarial training with adaptive step size
    Zhichao Huang, Yanbo Fan#, Chen Liu, Weizhong Zhang, Yong Zhang, Mathieu Salzmann, Sabine Süsstrunk, Jue Wang
    [Transactions on Image Processing (TIP 2023)]

11. NOFA: NeRF-based One-shot Facial Avatar Reconstruction.
    Wangbo Yu, Yanbo Fan#, Yong Zhang, Xuan Wang, Fei Yin, Yunpeng Bai, Yan-Pei Cao, Ying Shan, Yang Wu, Zhongqian Sun, Baoyuan Wu.
    [Siggraph 2023, conference paper]

12. High-fidelity Facial Avatar Reconstruction from Monocular Video with Generative Priors.
    Yunpeng Bai, Yanbo Fan#, Xuan Wang, Yong Zhang, Jingxiang Sun, Chun Yuan, Ying Shan
    [CVPR 2023]

13. DPE: Disentanglement of Pose and Expression for General Video Portrait Editing.
    Youxin Pang, Yong Zhang, Weize Quan, Yanbo Fan, Xiaodong Cun, Ying Shan, Dong-ming Yan
    [CVPR 2023] 

14. Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation.
    Zeyu Qin*, Yanbo Fan*, Yi Liu, Li Shen, Yong Zhang, Jue Wang, Baoyuan Wu.
    [NeurIPS 2022]

15. Stability Analysis and Generalization Bounds of Adversarial Training.
    Jiancong Xiao, Yanbo Fan#, Ruoyu Sun, Jue Wang, Zhi-Quan Luo.
    [NeurIPS 2022, spotlight] 

16. Robust Physical-World Attacks on Face Recognition.
    Xin Zheng*, Yanbo Fan*, Baoyuan Wu, Yong Zhang, Jue Wang, Shirui Pan.
    [Pattern Recognition 2022] 

17. VDTR: Video Deblurring with Transformer.
    Mingdeng Cao, Yanbo Fan#, Yong Zhang, Jue Wang, Yujiu Yang.
    [TCSVT 2022]

18. Generalizable Black-Box Adversarial Attack with Meta Learning.
    Fei Yin, Yong Zhang, Baoyuan Wu, Yan Feng, Jingyi Zhang, Yanbo Fan, Yujiu Yang.
    [T-PAMI 2022]

19. A Large-scale Multiple-objective Method for Black-box Attack against Object Detection.
    Siyuan Liang, Longkang Li, Yanbo Fan, Xiaojun Jia, Jingzhi Li, Baoyuan Wu, Xiaochun Cao.
    [ECCV 2022]

20. StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN.
    Fei Yin, Yong Zhang, Xiaodong Cun, Mingdeng Cao, Yanbo Fan, Xuan Wang, Qingyan Bai, Baoyuan Wu, Jue Wang, Yujiu Yang.
    [ECCV 2022]

21. HyP Loss: Beyond Hypersphere Metric Space for Multi-label Image Retrieval.
    Chengyin Xu, Zenghao Chai, Zhengzhuo Xu, Chun Yuan, Yanbo Fan#, Jue Wang
    [ACM MM 2022]

22. High-Fidelity GAN Inversion for Image Attribute Editing.
    Tengfei Wang, Yong Zhang, Yanbo Fan, Jue Wang, Qifeng Chen.
    [CVPR 2022]

23. Boosting Black-Box Attack with Partially Transferred Conditional Adversarial Distribution.
    Yan Feng, Baoyuan Wu, Yanbo Fan, Li Liu, Zhifeng Li, Shu-Tao Xia.
    [CVPR 2022] 

24. Random Noise Defense Against Query-Based Black-Box Attacks.
    Zeyu Qin, Yanbo Fan, Hongyuan Zha, Baoyuan Wu.
    [NeurIPS 2021] 

25. Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detection.
    Siyuan Liang, Baoyuan Wu, Yanbo Fan, Xingxing Wei, Xiaochun Cao.
    [ICCV 2021] 

26. DAE-GAN: Dynamic Aspect-aware GAN for Text-to-Image Synthesis.
    Shulan Ruan, Yong Zhang, Kun Zhang, Yanbo Fan, Fan Tang, Qi Liu, Enhong Chen.
    [ICCV 2021] 

27. Sparse Adversarial Attack via Perturbation Factorization.
    Yanbo Fan, Baoyuan Wu, Tuanhui Li, Yong Zhang, Mingyang Li, Zhifeng Li, Yujiu Yang.
    [ECCV 2020]

28. Average Top-k Loss for supervised learning
    Siwei Lyu, Yanbo Fan#, Yiming Ying, Bao-Gang Hu.
    [T-PAMI 2020]

29. 3D Single-Person Concurrent Activity Detection Using Stacked Relation Network.
    Yi Wei, Wenbo Li, Yanbo Fan, Linghan Xu, Ming-Ching Chang, Siwei Lyu.
    [AAAI 2020] 

30. Context-aware Feature and Label Fusion for Facial Action Unit Intensity Estimation with Partially Labeled Data.
    Yong Zhang, Haiyong Jiang, Baoyuan Wu, Yanbo Fan, Qiang Ji.
    [ICCV 2019] 

31. Adversarial Attack to Image Captioning via Structured Output Learning with Latent Variables.
    Yan Xu, Baoyuan Wu, Fumin Shen, Yanbo Fan, Yong Zhang, Heng Tao Shen and Wei Liu.
    [CVPR 2019] 

32. Compressing Convolutional Neural Networks via Factorized Convolutional Filters.
    Tuanhui Li, Baoyuan Wu, Yujiu Yang, Yanbo Fan, Yong Zhang, and Wei Liu.
    [CVPR 2019] 

33. Learning with Average Top-k Loss.
    Yanbo, Fan, Siwei Lyu, Yiming Ying and Bao-Gang Hu.
    [NeurIPS 2017] 

34. Self-Paced Learning: An Implicit Regularization Perspective.
    Yanbo, Fan, Ran He, Jian Liang and Bao-Gang Hu.
    [AAAI 2017] 

Services

• Area Chair: ICLR 2025/2026, ICME 2025, WACV 2025/2026

• Reviewers: Top-Tier Conferences and Journals of AI.