Hello! Iām Yuxuan Zhou(åØęč½© in Chinese), a first-year Ph.D. student at the Shenzhen International Graduate School, Tsinghua University, advised by Professor Shu-Tao Xia. I also worked as a Research Intern at Security Flow, ByteDance., mentored by Yang Bai and Dongxian Wu in 2025. I obtained my Bachelor of Engineering degree in Cybersecurity from Huazhong University of Science and Technology (HUST) in 2025.
My research focuses on AI security and privacy, and responsible generative AI. I strongly believe in the power of interdisciplinary collaboration and the potential it holds for driving impactful research outcomes. If you are interested in partnering on research projects, offering internship opportunities or exchange programs, I would be thrilled to connect with you.
š„ News
- 2025.12: Ā š One paper on BrowserAgent was accepted by TMLR!
- 2025.11: Ā š I joined EVOL-Lab at TeleAI as a research intern!
- 2025.11: Ā š One paper (as first author) on Deepfake Detection was accepted by AAAI 2026!
- 2025.06: Ā š I got my Bachelor of Engineering degree from Huazhong University of Science and Technology (HUST) and will start my Ph.D. studies in Augest 2025. Thank you to all my advisors and collaborators!
- 2025.03: Ā š One paper on Backdoor Sample Detection was accepted by IEEE Symposium on Security and Privacy (SP) 2025!
- 2025.03: Ā š I joined ByteDance as a research intern!
- 2024.11: Ā š One paper on Adversarial Example was accepted by AAAI 2025 as an Oral!
- 2024.07: Ā š„ Our work won Special Prize (only 12 in China) and First Prize in National College Student Information Security Competition.
- 2023.07: Ā š„ Our project was awarded national-level funding through the Undergraduate Innovation and Entrepreneurship Training Program.
š Publications
Improving Deepfake Detection with Reinforcement Learning-Based Adaptive Data Augmentation
Yuxuan Zhou, Tao Yu, Wen Huang, Yuheng Zhang, Tao Dai, Shu-Tao Xia
- Introducing a new RL-Based method to improve deepfake detection from the perspective of reducing the bias in different augmentation strategies.
š Other Papers
-
Arxiv JPRO: Automated Multimodal Jailbreaking via Multi-Agent Collaboration Framework
Yuxuan Zhou, Yang Bai, Kuofeng Gao, Tao Dai, Shu-Tao Xia -
Arxiv Why does weak-OOD help? A Further Step Towards Understanding Jailbreaking VLMs
Yuxuan Zhou, Yuzhao Peng, Yang Bai, Kuofeng Gao, Yihao Zhang, Yechao Zhang, Xun Chen, Tao Yu, Tao Dai, Shu-Tao Xia -
IEEE SP 2025 Secure Transfer Learning: Training Clean Model Against Backdoor in Pre-trained Encoder and Downstream Dataset
Yechao Zhang, Yuxuan Zhou, Tianyu Li, Minghui Li, Shengshan Hu, Wei Luo, Leo Yu Zhang -
AAAI 2025 oral Breaking barriers in physical-world adversarial examples: Improving robustness and transferability via robust feature
Yichen Wang, Yuxuan Chou, Ziqi Zhou, Hangtao Zhang, Wei Wan, Shengshan Hu, Minghui Li
š Honors and Awards
- 2024.07: The 17th National College Student Information Security Competition, Special Prize, First Prize. (First one in HUST)
- 2024.03: Qiushi Cup Silver Award. (Only one in the Department)
- 2023.07: National University Student Innovation & Entrepreneurship Development Program. (Only one in the Department)
- 2022.01: Shenyang Aircraft Corporation-Flying Shark Scholarship.
š Educations
- 2025.08 - Now, SIGS, Tsinghua University, Shenzhen, China.
- 2021.09 - 2025.06, Huazhong University of Science and Technology (HUST), Wuhan, China.