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 Sea AI Lab from 2024 to 2025, advised by Dr. Tianyu Pang and Dr. Chao Du.
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).
Publications
(* indicates equal contribution)
2025
-
QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language
Qingsong Zou, Jingyu Xiao, Qing Li, Zhi Yan, Yuhang Wang, Li Xu, Wenxuan Wang, Kuofeng Gao, Ruoyu Li, Yong Jiang
Annual Meeting of the Association for Computational Linguistics (ACL-Findings), 2025
[code]
[arxiv]
-
VLMInferSlow: Evaluating the Efficiency Robustness of Large Vision-Language Models as a Service
Xiasi Wang, Tianliang Yao, Simin Chen, Runqi Wang, Lei Ye, Kuofeng Gao, Yi Huang, Yuan Yao
Annual Meeting of the Association for Computational Linguistics (ACL), 2025
[code]
[arxiv]
-
Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models
Kuofeng Gao, Shu-Tao Xia, Ke Xu, Philip Torr, Jindong Gu
Annual Meeting of the Association for Computational Linguistics (ACL), 2025
[code]
[arxiv]
-
Protecting Your Video Content: Disrupting Automated Video-based LLM Annotations
Haitong Liu*, Kuofeng Gao*, Yang Bai, Jinmin Li, Jinxiao Shan, Tao Dai, Shu-Tao Xia
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025
[code]
[arxiv]
2024
-
LLM Safety and Ethics (in Chinese)
Kuofeng Gao, Linghui Zhu, Yuqi Tan, Sheng Yang, Yuang Peng, Wen Huang, Yiming Li, Shu-Tao Xia
Technical Report, 2024
[arxiv]
-
Pointncbw: Towards Dataset Ownership Verification for Point Clouds via Negative Clean-label Backdoor Watermark
Cheng Wei, Yang Wang, Kuofeng Gao, Shuo Shao, Yiming Li, Zhibo Wang, Zhan Qin
IEEE Transactions on Information Forensics and Security (TIFS), 2024
[code]
[arxiv]
-
Video Watermarking: Safeguarding Your Video from (Unauthorized) Annotations by Video-based LLMs
Jinmin Li, Kuofeng Gao, Yang Bai, Jingyun Zhang, Shu-Tao Xia
ICML 2024 Workshop on Trustworthy Multi-modal Foundation Models and AI Agents, 2024
[code]
[arxiv]
-
Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transformers
Sheng Yang, Jiawang Bai, Kuofeng Gao, Yong Yang, Yiming Li, Shu-Tao Xia
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
[code]
[arxiv]
-
BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP
Jiawang Bai*, Kuofeng Gao*, Shaobo Min, Shu-Tao Xia, Zhifeng Li, Wei Liu
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
[code]
[arxiv]
-
Adversarial Robustness for Visual Grounding of Multimodal Large Language Models
Kuofeng Gao, Yang Bai, Jiawang Bai, Yong Yang, Shu-Tao Xia
ICLR 2024 Workshop on Reliable and Responsible Foundation Models, 2024
[code]
[arxiv]
-
Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images
Kuofeng Gao, Yang Bai, Jindong Gu, Shu-Tao Xia, Philip Torr, Zhifeng Li, Wei Liu
International Conference on Learning Representations (ICLR), 2024
[code]
[arxiv]
2023
-
Backdoor Defense via Adaptively Splitting Poisoned Dataset
Kuofeng Gao, Yang Bai, Jindong Gu, Yong Yang, Shu-Tao Xia
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023
[code]
[arxiv]
-
Imperceptible and Robust Backdoor Attack in 3D Point Cloud
Kuofeng Gao, Jiawang Bai, Baoyuan Wu, Mengxi Ya, Shu-Tao Xia
IEEE Transactions on Information Forensics and Security (TIFS), 2023
[code]
[arxiv]
-
Backdoor Attack on Hash-based Image Retrieval via Clean-label Data Poisoning
Kuofeng Gao, Jiawang Bai, Bin Chen, Dongxian Wu, Shu-Tao Xia
British Machine Vision Conference (BMVC), 2023
[code]
[arxiv]
2022
-
Practical Protection against Video Data Leakage via Universal Adversarial Head
Jiawang Bai, Bin Chen, Kuofeng Gao, Xuan Wang, Shu-Tao Xia
Pattern Recognition (PR), 2022
-
Hardly Perceptible Trojan Attack against Neural Networks with Bit Flips
Jiawang Bai, Kuofeng Gao, Dihong Gong, Shu-Tao Xia, Zhifeng Li, Wei Liu
European Conference on Computer Vision (ECCV), 2022
[code]
[arxiv]
Honors & Awards
-
Excellent Science & Technology Papers (1/100), Shenzhen Association for Science and Technology, 2024
-
First Prize Scholarship (Top 20%), SIGS, Tsinghua University, 2024
-
Future Scholar Ph.D. Scholarship (Top 1%), Tsinghua University, 2024
-
First Prize Scholarship (Top 10%), Tsinghua University, 2024
-
Tencent Rhino-Bird Elite Talent (Top 50+ in China), Tencent, 2023
-
Finalist (Top 1%), Mathematical Contest In Modeling / Interdisciplinary Contest In Modeling, 2020
-
LuoGe-TianYou Scholarship (Top 1%), Wuhan University, 2020
-
Liu DaoYu Scholarship (Top 1%), Wuhan University, 2020
-
LuoJia Excellent Exchange Scholarship (Top 10%), Wuhan University, 2019
-
National Scholarship (Top 0.2%), Ministry of Education of China, 2019
Services
I was a reviewer / PC member of conferences:
-
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2024-2025
-
European Conference on Computer Vision (ECCV) 2024
-
International Conference on Computer Vision (ICCV) 2025
-
ACM Multimedia (MM) 2024-2025
-
Neural Information Processing Systems (NeurIPS) 2024-2025
-
Neural Information Processing Systems Datasets and Benchmarks Track (NeurIPS D&B) 2024
-
International Conference on Learning Representations (ICLR) 2025
-
International Conference on Machine Learning (ICML) 2025
-
Artificial Intelligence and Statistics (AISTATS) 2025
I was a reviewer of journals:
-
IEEE Transactions on Information Forensics & Security (TIFS)
-
IEEE Transactions on Dependable and Secure Computing (TDSC)
-
IEEE Transactions on Multimedia (TMM)
-
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
-
Pattern Recognition (PR)
Teaching
2024 Fall, TA in Applied Information Theory, instructed by Prof. Shu-Tao Xia
© 2025 Kuofeng Gao