I am a tenure-track associate professor of computer science at Fudan University and a member of Fudan Vision and Learning (FVL) Lab. I am also an honorary fellow at The University of Melbourne. My main research area is Trustworthy AI, aiming to develop secure, robust, explainable, privacy-preserving, and fair learning algorithms and AI models for different applications. I am also deeply passionate about leveraging AI to deepen our understanding of the mind and the universe.
I received my Ph.D. degree from The University of Melbourne and spent another 2 wonderful years as a postdoctoral research fellow. I worked for 1.5 years at Deakin University as a lecturer before joining Fudan University. I obtained my bachelor's and master's degrees from Jilin University and Tsinghua University, respectively.
"Everything should be as simple as possible, but not simpler."
Email / Google Scholar / GitHub
We are looking for motivated students, postdocs, and interns in the field of Trustworthy AI, Multimodal Learning, Reinforcement Learning, and Generative AI to join our team. Drop me an email if you are interested.
Books
Latest News
- [12/2024] I will serve as an Area Chair for ICML 2025.
- [12/2024] Our works on transferable adversarial attack, defense against model extraction attacks, and RL-based LLM auditing are accepted by AAAI 2025.
- [09/2024] I will serve as an Area Chair for ICLR 2025.
- [09/2024] One paper on unlearnable examples for segmentation models is accepted to NeurIPS, 2024.
- [07/2024] Our works on model lock , detecting query-based adversarial attacks , and multimodal jailbreak attacks on VLMs are accepted by MM'24.
- [07/2024] Our work on adversarial prompt tuning is accepted by ECCV'24.
- [04/2024] Our work on intrinsic motivation for RL is accepted by IJCAI'24.
- [03/2024] Our work on adversarial policy learning in RL is accepted by DSN'24.
- [03/2024] Our work on safety alignment of LLMs is accepted by NAACL'24.
- [03/2024] Our work on machine unlearning is accepted by TDSC.
- [01/2024] Our work on self-supervised learning is accepted by ICLR'24.
Research Interests
- Trustworthy AI
- Adversarial/jailbreak attacks and defenses
- Backdoor attacks and defenses
- Reinforcement learning, safety alignment
- Data privacy, data/model extraction
- Memorization, data attribution, unlearning
- Multimodal and Generative AI
- Multimodal learning, vision-language models
- Diffuson models, Text2Image generation, Text2Video generation
- World model, embodied AI
Professional Activities
- Program Committee Member
- ICLR (2019-2025), ICML (2019-2025), NeurIPS (2019-2024), CVPR (2020-2025), ICCV (2021-2023), ECCV (2020), AAAI (2020-2022), IJCAI (2020-2021), KDD (2019,2021), ICDM (2021), SDM (2021), AICAI (2021)
- Journal Reviewer
- Nature Communications, Pattern Recognition, TPAMI, TIP, IJCV, JAIR, TNNLS, TKDE, TIFS, TOMM, KAIS