Improving Adversarial Robustness via Channel-wise Activation Suppressing Y Bai, Y Zeng, Y Jiang, ST Xia, X Ma, Y Wang The International Conference on Learning Representations (ICLR), 2021, 2021 | 144 | 2021 |
Untargeted backdoor watermark: Towards harmless and stealthy dataset copyright protection Y Li, Y Bai, Y Jiang, Y Yang, ST Xia, B Li Advances in Neural Information Processing Systems 35, 13238-13250, 2022 | 98 | 2022 |
Query efficient black-box adversarial attack on deep neural networks Y Bai, Y Wang, Y Zeng, Y Jiang, ST Xia Pattern Recognition 133, 109037, 2023 | 65 | 2023 |
Improving Query Efficiency of Black-box Adversarial Attack Y Bai, Y Zeng, Y Jiang, Y Wang, ST Xia, W Guo European Conference on Computer Vision (ECCV), 2020, 2020 | 62 | 2020 |
Hilbert-based Generative Defense for Adversarial Examples Y Bai, Y Feng, Y Wang, T Dai, ST Xia, Y Jiang Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2019 | 60 | 2019 |
Backdoor Defense via Adaptively Splitting Poisoned Dataset K Gao, Y Bai, J Gu, Y Yang, ST Xia Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023 | 59 | 2023 |
BackdoorBox: A python toolbox for backdoor learning Y Li, M Ya, Y Bai, Y Jiang, ST Xia ICLR 2023 Workshop on Backdoor Attacks and Defenses in Machine Learning, 2023 | 41 | 2023 |
Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images K Gao, Y Bai, J Gu, ST Xia, P Torr, Z Li, W Liu The International Conference on Learning Representations (ICLR), 2024, 2024 | 35 | 2024 |
Watermark vaccine: Adversarial attacks to prevent watermark removal X Liu, J Liu, Y Bai, J Gu, T Chen, X Jia, X Cao European Conference on Computer Vision, 1-17, 2022 | 28 | 2022 |
OT-Attack: Enhancing Adversarial Transferability of Vision-Language Models via Optimal Transport Optimization D Han, X Jia, Y Bai, J Gu, Y Liu, X Cao arXiv preprint arXiv:2312.04403, 2023 | 18 | 2023 |
Clustering Effect of (Linearized) Adversarial Robust Models Y Bai, X Yan, Y Jiang, ST Xia, Y Wang Thirty-Fifth Conference on Neural Information Processing Systems (NeurIPS), 2021, 2021 | 17* | 2021 |
Adversarial Robustness for Visual Grounding of Multimodal Large Language Models K Gao, Y Bai, J Bai, Y Yang, ST Xia arXiv preprint arXiv:2405.09981, 2024 | 16 | 2024 |
Energy-Latency Manipulation of Multi-modal Large Language Models via Verbose Samples K Gao, J Gu, Y Bai, ST Xia, P Torr, W Liu, Z Li arXiv preprint arXiv:2404.16557, 2024 | 12 | 2024 |
MOVE: Effective and Harmless Ownership Verification via Embedded External Features Y Li, L Zhu, X Jia, Y Bai, Y Jiang, ST Xia, X Cao arXiv preprint arXiv:2208.02820, 2022 | 12 | 2022 |
Special Characters Attack: Toward Scalable Training Data Extraction From Large Language Models Y Bai, G Pei, J Gu, Y Yang, X Ma arXiv preprint arXiv:2405.05990, 2024 | 10 | 2024 |
Cheating Suffix: Targeted Attack to Text-To-Image Diffusion Models with Multi-Modal Priors D Yang, Y Bai, X Jia, Y Liu, X Cao, W Yu arXiv preprint arXiv:2402.01369, 2024 | 8* | 2024 |
On the Multi-modal Vulnerability of Diffusion Models D Yang, Y Bai, X Jia, Y Liu, X Cao, W Yu Trustworthy Multi-modal Foundation Models and AI Agents (TiFA), 2024 | 5 | 2024 |
Video Watermarking: Safeguarding Your Video from (Unauthorized) Annotations by Video-based LLMs J Li, K Gao, Y Bai, J Zhang, ST Xia arXiv preprint arXiv:2407.02411, 2024 | 2 | 2024 |
Test-time Adaptation of Residual Blocks against Poisoning and Backdoor Attacks A Gudibande, X Chen, Y Bai, J Xiong, D Song CVPR Workshop, 2022, 2022 | 2 | 2022 |
D2Defend: Dual-Domain based Defense against Adversarial Examples X Yan, Y Li, T Dai, Y Bai, ST Xia 2021 International Joint Conference on Neural Networks (IJCNN), 1-8, 2021 | 2 | 2021 |