Publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2024

  1. Video Watermarking: Safeguarding Your Video from (Unauthorized) Annotations by Video-based LLMs
    Jinmin Li ,  Kuofeng Gao ,  Yang Bai , and 2 more authors
    In ICML 2024 Workshop on Trustworthy Multi-modal Foundation Models and AI Agents , 2024
    PDF
  2. Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transformers
    Sheng Yang ,  Jiawang Bai ,  Kuofeng Gao , and 3 more authors
    In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2024
    PDF Code
  3. BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP
    Jiawang Bai* ,  Kuofeng Gao* ,  Shaobo Min , and 3 more authors
    In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2024
    PDF Code
  4. Adversarial Robustness for Visual Grounding of Multimodal Large Language Models
    Kuofeng Gao ,  Yang Bai ,  Jiawang Bai , and 2 more authors
    In ICLR 2024 Workshop on Reliable and Responsible Foundation Models , 2024
    PDF
  5. 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
    PDF Code

2023

  1. 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
    PDF Code
  2. 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
    PDF Code
  3. Backdoor Attack on Hash-based Image Retrieval via Clean-label Data Poisoning
    Kuofeng Gao ,  Jiawang Bai ,  Bin Chen , and 2 more authors
    In British Machine Vision Conference (BMVC) , 2023
    PDF Code

2022

  1. Practical Protection against Video Data Leakage via Universal Adversarial Head
    Jiawang Bai ,  Bin Chen ,  Kuofeng Gao , and 2 more authors
    Pattern Recognition, 2022
    PDF
  2. Hardly Perceptible Trojan Attack against Neural Networks with Bit Flips
    Jiawang Bai ,  Kuofeng Gao ,  Dihong Gong , and 3 more authors
    In European Conference on Computer Vision (ECCV) , 2022
    PDF Code