| Backdoor Defense via Adaptively Splitting Poisoned Dataset K Gao, Y Bai, J Gu, Y Yang, ST Xia IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023 | 57 | 2023 |
| Imperceptible and Robust Backdoor Attack in 3D Point Cloud K Gao, J Bai, B Wu, M Ya, ST Xia IEEE Transactions on Information Forensics and Security (TIFS), 2022 | 35 | 2022 |
| 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 International Conference on Learning Representations (ICLR), 2024 | 31 | 2024 |
| BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP J Bai, K Gao, S Min, ST Xia, Z Li, W Liu IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024 | 30 | 2024 |
| Hardly perceptible trojan attack against neural networks with bit flips J Bai, K Gao, D Gong, ST Xia, Z Li, W Liu European Conference on Computer Vision (ECCV), 2022 | 30 | 2022 |
| Adversarial Robustness for Visual Grounding of Multimodal Large Language Models K Gao, Y Bai, J Bai, Y Yang, ST Xia ICLR 2024 Workshop on Reliable and Responsible Foundation Models, 2024 | 14 | 2024 |
| Backdoor Attack on Hash-based Image Retrieval via Clean-label Data Poisoning K Gao, J Bai, B Chen, D Wu, ST Xia British Machine Vision Conference (BMVC), 2021 | 14* | 2021 |
| 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 |
| Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas C Deng, Y Duan, X Jin, H Chang, Y Tian, H Liu, HP Zou, Y Jin, Y Xiao, ... arXiv preprint arXiv:2406.05392, 2024 | 11 | 2024 |
| Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transformers S Yang, J Bai, K Gao, Y Yang, Y Li, S Xia IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024 | 8 | 2024 |
| Practical protection against video data leakage via universal adversarial head J Bai, B Chen, K Gao, X Wang, ST Xia Pattern Recognition, 2022 | 5 | 2022 |
| Video Watermarking: Safeguarding Your Video from (Unauthorized) Annotations by Video-based LLMs J Li, K Gao, Y Bai, J Zhang, ST Xia ICML 2024 Workshop on Trustworthy Multi-modal Foundation Models and AI Agents, 2024 | 4* | 2024 |
| Pointncbw: Towards dataset ownership verification for point clouds via negative clean-label backdoor watermark C Wei, Y Wang, K Gao, S Shao, Y Li, Z Wang, Z Qin IEEE Transactions on Information Forensics and Security (TIFS), 2024 | 3 | 2024 |
| Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models K Gao, ST Xia, K Xu, P Torr, J Gu arXiv preprint arXiv:2412.05167, 2024 | 1 | 2024 |
| Denial-of-Service Poisoning Attacks against Large Language Models K Gao, T Pang, C Du, Y Yang, ST Xia, M Lin arXiv preprint arXiv:2410.10760, 2024 | | 2024 |
Shu-Tao XiaSIGS, Tsinghua UniversityEmail verificata su sz.tsinghua.edu.cn