Hi there 👋👋 !

I’m Boheng Li (李勃衡), a third-year Ph.D. candidate at the College of Computing and Data Science (CCDS), Nanyang Technological University, Singapore, under the supervision of Prof. Tianwei Zhang. I received my B.E. from the School of Cyber Science and Engineering (SCSE), Wuhan University (WHU), China, where I was advised by Prof. Run Wang. During my undergraduate studies, I also worked as a research intern at the State Key Laboratory of Blockchain and Data Security, Zhejiang University, China, collaborating with Dr. Yiming Li.

My research centers on responsible (multimodal) generative models, i.e., the security and intellectual property (IP) protection of generative AI. I study how the misuse of data and models can be detected, verified, and defended against in the era of generative models, spanning offensive (red-teaming), defensive (safety alignment and data protection), and auditing (provenance and ownership verification) perspectives. I am particularly drawn to observation- and insight-driven research. I enjoy reading (and writing) papers that distill careful observations or principled reasoning into methods that are simple by design yet backed by theoretical guarantees.

🌟🌟 I am open to discussions and potential collaboration opportunities. If you’re interested in working with me, feel free to contact me via Email or WeChat.

🔥 News

📝 Selected Publications

$^\dagger$: equal contribution

• DREAM: Scalable Red Teaming for Text-to-Image Generative Systems via Distribution Modeling
  Boheng Li, Junjie Wang, Yiming Li, Zhiyang Hu, Leyi Qi, Jianshuo Dong, Run Wang, Han Qiu, Zhan Qin, Tianwei Zhang
  The IEEE Symposium on Security and Privacy (S&P), 2026

• Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning
  Boheng Li, Renjie Gu, Junjie Wang, Leyi Qi, Yiming Li, Run Wang, Zhan Qin, Tianwei Zhang
  Annual Conference on Neural Information Processing Systems (NeurIPS), 2025

• Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack
  Yukun Chen$^\dagger$, Boheng Li$^\dagger$, Yu Yuan$^\dagger$, Leyi Qi, Yiming Li, Tianwei Zhang, Zhan Qin, Kui Ren
  Annual Conference on Neural Information Processing Systems (NeurIPS), 2025

• Towards Reliable Verification of Unauthorized Data Usage in Personalized Text-to-Image Diffusion Models
  Boheng Li, Yanhao Wei, Yankai Fu, Zhenting Wang, Yiming Li, Jie Zhang, Run Wang, Tianwei Zhang
  The IEEE Symposium on Security and Privacy (S&P), 2025

• Purifying Quantization-conditioned Backdoors via Layer-wise Activation Correction with Distribution Approximation
  Boheng Li$^\dagger$, Yishuo Cai$^\dagger$, Jisong Cai, Yiming Li, Han Qiu, Run Wang, Tianwei Zhang
  The International Conference on Machine Learning (ICML), 2024

• Nearest Is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks
  Boheng Li, Yishuo Cai, Haowei Li, Feng Xue, Zhifeng Li, Yiming Li
  The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

• Is Difficulty Calibration All We Need? Towards More Practical Membership Inference Attacks
  Yu He$^\dagger$, Boheng Li$^\dagger$, Yao Wang, Mengda Yang, Juan Wang, Hongxin Hu, Xingyu Zhao
  The ACM Conference on Computer and Communications Security (CCS), 2024

• What can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial Networks
  Ziheng Huang$^\dagger$, Boheng Li$^\dagger$, Yan Cai, Run Wang, Shangwei Guo, Liming Fang, Jing Chen, Lina Wang
  The International Conference on Computer Vision (ICCV), 2023

🏆 Selected Awards

• 🏅 Champion (1st Place) of both the Preliminary (Phase 1, white-box) and Final (Phase 2, overall) phases, LifeGenIP Challenge: Unlearnable Videos against Diffusion-based Customization @ ECCV 2026, team leader. 2026.08
• Top 200 Reviewers Award, ICLR 2026. 2026.04
• Top Reviewer Award, NeurIPS 2025. 2025.10
• Top Reviewer Award, ICML 2025. 2025.05
• Notable Reviewer Award, ICLR 2025. 2025.05
• Outstanding Reviewer Award, ACM MM 2024. 2024.11
• National Scholarship (top 0.2% nationwide), Ministry of Education, China. 2023.10
• National Scholarship (top 0.2% nationwide), Ministry of Education, China. 2022.10

📖 Education

• 2024.08 - Now, Ph.D. candidate, College of Computing and Data Science, Nanyang Technological University, Singapore.
• 2020.09 - 2024.06, Undergraduate, School of Cyber Science and Engineering, Wuhan University, China.

🎡 Activities

Academic Services

Program & Evaluation Committee

• Program Committee, The ACM Conference on Computer and Communications Security (CCS), 2026.
• Program Committee, IEEE European Symposium on Security and Privacy (EuroS&P), 2026.
• Program Committee, IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), 2026, 2027.
• Program Committee, The IEEE Annual Computer Security Applications Conference (ACSAC), 2026.
• Artifact Evaluation Committee, Network and Distributed System Security Symposium (NDSS), 2026.
• Artifact Evaluation Committee, USENIX Security Symposium (USENIX Security), 2025.

Conference Reviewer

• International Conference on Machine Learning (ICML), 2025, 2026.
• International Conference on Learning Representations (ICLR), 2025, 2026, 2027.
• Annual Conference on Neural Information Processing Systems (NeurIPS), 2024, 2025.
• IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
• IEEE/CVF International Conference on Computer Vision (ICCV), 2025.
• ACM Multimedia Conference (ACM MM), 2024, 2025.
• The European Conference on Computer Vision (ECCV), 2026.
• International Conference on Artificial Intelligence and Statistics (AISTATS), 2025, 2026.
• International Conference on Multimedia Retrieval (ICMR), 2026.

Journal Reviewers

• IEEE S&P Magazine, 2026.
• Transactions on Machine Learning Research (TMLR), 2025.
• IEEE Transactions on Dependable and Secure Computing (TDSC), 2025.
• IEEE Transactions on Information Forensics & Security (TIFS), 2025.
• IEEE Transactions on Image Processing (TIP), 2025.
• IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025.
• ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2023.