Renshuai Tao
陶仁帅,rstao@bjtu.edu.cn

I am an Associate Professor at the School of Computer Science and Technology, BJTU, working in collaboration with Prof. Yao Zhao (IEEE Fellow). I received my B.S. and Ph.D. degrees from BUAA in 2017 and 2022, respectively, under the supervision of Prof. Wei Li (Academician of Chinese Academy of Sciences) and Prof. Xianglong Liu. Previously, I was a Senior Researcher at Noah’s Ark Lab, Huawei, collaborating with Dr. Yunhe Wang.
My research focuses on two major directions: AI Robustness and Forensics. The first addresses AI safety and security, with an emphasis on DeepFake detection and open-world learning. In this context, I explore techniques such as open-set learning, domain adaptation, and few-shot learning to enhance machine learning models’ adaptability to real-world scenarios. The second centers on model privacy protection, including copyright preservation through mechanisms like backdoor attacks. In addition, I work on evaluation benchmarking, developing rigorous assessment frameworks for critical yet underexplored challenges to foster progress and innovation in the field.
[Prospective students] Our group (BJTU) has positions for PhD students, Master students, and visiting students. If you are interested, please feel free to send me an email with your CV and publications (if any).
news
Jun 10, 2025 | One paper is accepted by TIFS (IEEE Transactions on Information Forensics and Security). Congrates to all co-authors! |
---|---|
Apr 29, 2025 | One paper is accepted by IJCAI 2025. Congrates to Ziheng and other co-authors! |
Apr 20, 2025 | One paper is accepted by SCIS (SCIENCE CHINA Information Science). Congrates to Shijie and other co-authors! |
Feb 27, 2025 | One paper is accepted by CVPR 2025. Congrates to Haoyu, Yuzhe, Hairong and other co-authors! |
Dec 14, 2024 | One paper is accepted by IEEE TMM. |
Dec 10, 2024 | Four papers are accepted by AAAI 2025 (oral presentation, 4.6%). Congrates to Manyi, Chuangchuang and other co-authors! |
Apr 16, 2024 | One paper is accepted by IJCAI 2024. |
Nov 07, 2023 | I join BJTU as an Associate Professor. |
selected publications
- AAAIC2p-clip: Injecting category common prompt in clip to enhance generalization in deepfake detectionIn Proceedings of the AAAI Conference on Artificial Intelligence, 2025
- TIFSSAGNet: Decoupling Semantic-Agnostic Artifacts from Limited Training Data for Robust Generalization in Deepfake DetectionIEEE Transactions on Information Forensics & Security, 2025
- SCISLEDNet: A Multimodal Foundation Model for Robust Deepfake DetectionIn SCIENCE CHINA Information Science, 2025
- IJCAIUnlocking the Potential of Lightweight Quantized Models for Deepfake DetectionIn 34th International Joint Conference on Artificial Intelligence (IJCAI), 2025