Greetings and Welcome to My Homepage

Biography

I am currently a Research Professor (求是科创学者) at the School of Cyber Science and Technology, Zhejiang University. Before that, I received my Ph.D. degree with honors in Computer Science and Technology from Tsinghua University in 2023, advised by Prof. Yong Jiang and Prof. Shu-Tao Xia. I received my B.S. degree with honors in Applied Mathematics from Ningbo University in 2018, advised by Prof. Lifeng Xi.

I collaborated with Prof. Bo Li as a visiting Ph.D. student (online) from 2021 to 2023 at UIUC. I was a research intern at Ant Group from 2021 to 2023. I was a research intern at Tencent AI Lab under the Rhino-bird Elite Program from 2019 to 2020. I also worked closely with Dr. Zhifeng Li during my Ph.D. journey.

My research mainly focuses on Trustworthy AI, especially backdoor attacks/defenses and copyright protection in deep learning. My long-term goal is to make DL-based algorithms more robust and secure during their full life cycle. Recently, I focus more on Trustworthy Large Foundation Models (e.g., GPT-4). I always chase for simple yet effective methods with deep insights and theoretical supports.

Annocement

I am always looking for highly self-motivated students and research interns to join exciting research projects on Trustworthy AI in our group. Besides, I am always willing to work together on interesting projects with external collaborators. Drop me an email if you are interested!

News

  • 09/2023: I will give an invited talk about backdoor attacks for dataset copyright protection at NeurIPS’23 Backdoor Workshop. See you in New Orleans!
  • 09/2023: Two papers are accepted by NeurIPS 2023. Their codes will be released soon.
  • 07/2023: Two papers are accepted by ICCV 2023. Their codes have been released.
  • 06/2023: So exciting to receive the Rising Star Award from WAIC’23.
  • 05/2023: So exciting to receive the Best Paper Award from PAKDD’23.

Useful Resources

BackdoorBox: A Python Toolbox for Backdoor Attacks and Defenses

Github Repo about Backdoor Learning Resources

Technical Report about the ATT&CK Matrix of AI Security