I’m a junior year undergraduate from TSAIL, with keen interest in Trustworthy ML and diffusion models. My aspiration is to elevate AI to the realm of science, moving beyond its current engineering-focused approach. My preferred research paradigm involves observing phenomena, proposing multiple explanations, constructing various theories, validating corollaries, and ultimately deriving solutions or methodologies. I’m eager to connect with anyone who shares this vision for AI or appreciates the same research approach.
📝 Papers in Generative/Discriminative Learning Unification
Your Diffusion Model is Secretly a Certifiably Robust Classifier
Huanran Chen, Yinpeng Dong, Shitong Shao, Zhongkai Hao, Xiao Yang, Hang Su, Jun Zhu
- [arxiv]
Robust Classification via a Single Diffusion Model
Huanran Chen, Yinpeng Dong, Zhengyi Wang, Xiao Yang, Chengqi Duan, Hang Su, Jun Zhu
- [ICML2024]
📝 Papers in Optimization/Generalization
(*: Equal Contribution; ${}^\dagger$: Corresponding Author)
How Robust is Google’s Bard to Adversarial Image Attacks?
Yinpeng Dong, Huanran Chen, Jiawei Chen, Zhengwei Fang, Xiao Yang, Yichi Zhang, Yu Tian, Hang Su, Jun Zhu
Rethinking Model Ensemble in Transfer-based Adversarial Attacks
Huanran Chen, Yichi Zhang, Yinpeng Dong, Jun Zhu
- [ICLR2024]
Teach What You Should Teach: A Data-based Distillation Method.
Shitong Shao, Huanran Chen, Zhen Huang, Lirui Gong, Shuai Wang, Xinxiao Wu
- [IJCAI2023] (oral)
T-SEA: Transfer-based Self-Ensemble Attack on Object Detection
Hao Huang*, Ziyan Chen*, Huanran Chen*, Yongtao Wang, Kevin Zhang
- [CVPR2023]
Bootstrap Generalization Ability from Loss Landscape Perspective
Huanran Chen, Shitong Shao, Ziyi Wang, Zirui Shang, Jin Chen, Xiaofeng Ji, Xinxiao Wu
On the Duality Between Sharpness-Aware Minimization and Adversarial Training
Yihao Zhang, Hangzhou He, Jingyu Zhu, Huanran Chen, Yifei Wang, Zeming Wei
- [ICML2024]
Enhancing Adversarial Attacks: The Similar Target Method
Shuo Zhang, Ziruo Wang, Zikai Zhou, Huanran Chen${}^\dagger$
📖 Internships
- 2022.11 - present, Research Intern at TSAIL, Tsinghua University. Advised by Prof. Jun Zhu
- 2022.06 - 2022.11, Research Intern at VDIG, Wangxuan Institute, Peking University. Advised by Prof. Yongtao Wang
- 2022.02 - 2022.06, Research Intern at MCISLAB, Beijing Institute of Technology. Advised by Prof. Xinxiao Wu
💻 Projects
Adversarial Attacks package
- [code]
Attacks on GPT-4 and Bard
- [code]
Adversarial Attacks on Object Detection
- [code]
Landscape Visualization
- [code]
💼 Academic Service
- Conference Reviewer in ICLR 2024, ACMMM 2024, ECCV 2024
- Workshop Reviewer in NeurIPS2023-R0-FoMo, ICLR2024-BGPT, ICLR2024-SeT
- Reviewer in ICPR 2024, ICME 2024
🔥 Links
- Advisor: [Yinpeng Dong], [Jun Zhu]
- Friends: [Ziruo Wang], [Zeming Wei], [Zhengyi Wang], [Shitong Shao]
📧 Emails
I truly believe that great ideas and improvements come from open discussions and debates in academia. If you have any thoughts, disagreements with my work, or fresh ideas you’d like to share, I’d be really grateful to hear from you.
If you’ve got any questions about my research or if you’ve tried reaching out through GitHub issues and haven’t heard back, please don’t hesitate to drop me an email. I’m always here to chat or help out in any way I can.
My preferred email: huanran_chen@outlook.com
Please avoid sending emails to huanranchen@bit.edu.cn, as I won’t be able to access this account much longer.