Kuofeng Gao

Ph.D. Student at ITML Group, Tsinghua University.

Biography: I am currently pursuing my Ph.D. degree in Computer Science and Technology at Tsinghua University, advised by Prof. Shu-Tao Xia. I was a research intern at Tencent Hunyuan Group, Tencent from 2023 to 2024, advised by Dr. Zhifeng Li and Dr. Wei Liu. I obtained my Bachelor’s degree in Computer Science from Wuhan University, advised by Prof. Zhibo Wang.

My research mainly focuses on Trustworthy ML and Responsible AI, especially adversarial learning and backdoor learning. Recently, I focus more on Trustworthy Large Foundation Models (e.g., LLMs and Diffusion Model).

News

Feb 27, 2024 Two papers are accepted by CVPR 2024
Jan 17, 2024 One paper is accepted by ICLR 2024

Selected publications

  1. Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images
    Kuofeng Gao ,  Yang Bai ,  Jindong Gu , and 4 more authors
    In International Conference on Learning Representations (ICLR) , 2024
  2. Backdoor Defense via Adaptively Splitting Poisoned Dataset
    Kuofeng Gao ,  Yang Bai ,  Jindong Gu , and 2 more authors
    In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2023
  3. Imperceptible and Robust Backdoor Attack in 3D Point Cloud
    Kuofeng Gao ,  Jiawang Bai ,  Baoyuan Wu , and 2 more authors
    IEEE Transactions on Information Forensics and Security (TIFS), 2023