Jie Gui


Adversarial Attack and Defense


Survey

  • Survey of adversarial robustness in multimodal large language models
    C Jiang, Z Wang, M Dong, J Gui
    https://arxiv.org/abs/2503.13962


Algorithms

  • Improving Fast Adversarial Training Paradigm: An Example Taxonomy Perspective
    J Gui , C. Jiang, M. Dong, K. Tong, X. Shi, Y. Tang, D. Tao
    IEEE Transactions on Dependable and Secure Computing, 2025. accepted. [Code]

  • Gradient Perturbation Guidance for Boosting Sparse Adversarial Attack Transferability
    C. Jiang, Z. Wang, M. Dong, J. Gui*, L. Dong, Y. Tang, J. Kwok,
    IEEE Transactions on Circuits and Systems for Video Technology, 2025. accepted. [Code]

  • Diversifying Counterattacks: Orthogonal Exploration for Robust CLIP Inference. [Oral]
    C. Jiang, M. Dong, X. Shi, J. Gui*.
    AAAI Conference on Artificial Intelligence (AAAI), 2026. [Code]
    News: 我爱计算机视觉

  • Revisiting the Adversarial Transferability: Towards a Perspective of Semantic Preservation
    Z. Wang, C. Jiang, J. Gui*, X. Shi, Y. Tang,
    IEEE Transactions on Multimedia, 2025. accepted.

  • Unrevealed Threats: A Comprehensive Study of the Adversarial Robustness of Underwater Image Enhancement Models
    S. Zhai, Z. He, X. Cong, J. Hou, J. Gui*, J. You, X. Gong, J. Kwok, Y. Tang
    IEEE Transactions on Multimedia, vol. 27, pp. 9532-9541, 2025. [Code]

  • Divide and Conquer: Frequency-Aware Contrastive Adversarial Training for Robust Point Cloud Classification
    Y. Zhang, J. Gui*, M. Dong, X. Cong, Y. Cao, X. Gong, Y. Tang, J. Kwok
    IEEE Transactions on Information Forensics and Security, vol. 20, pp. 7709-7723, 2025.

  • Improving Fast Adversarial Training via Self-Knowledge Guidance
    C. Jiang, J. Wang, M. Dong, J. Gui*, X. Shi, Y. Cao, Y. Tang, J. Kwok
    IEEE Transactions on Information Forensics and Security, vol. 20, pp. 3772-3787, 2025. [Code]

  • Taxonomy Driven Fast Adversarial Training.
    K. Tong, C. Jiang, J. Gui*, Y. Cao.
    AAAI Conference on Artificial Intelligence (AAAI), 2024. [Code], [English video]

  • Fooling the Image Dehazing Models by First Order Gradient
    J. Gui, X. Cong, C. Peng, Y. Tang, J. Kwok
    IEEE Transactions on Circuits and Systems for Video Technology, vol. 34, no. 7, pp. 6265-6278, 2024. [Code]
    Paper: arxiv
    Video: Video (讲解视频), Valse论文速览