Tianhang Zheng

About Me

浙江大学百人研究员/博导，国家级青年人才，博士毕业于加拿大多伦多大学。研究方向包括大模型安全、大模型训练等。

招生信息：我正在积极招聘博士、硕士以及研究助理，欢迎具有扎实数学或计算机科学背景的同学联系我。本科生如对 AI 安全感兴趣，也欢迎随时沟通。

Service

Serve as AC for ICML, ICLR and NeurIPS

Serve as SPC for AAAI

Serve as Associate Editor for IEEE TCSVT

Publications (not a complete list):

• Xiaoyu Wen, Zhida He, Han Qi, Ziyu Wan, Zhongtian Ma, Ying Wen, Tianhang Zheng, Xingcheng Xu, Chaochao Lu, Qiaosheng Zhang, "MAGIC: A Co-Evolving Attacker–Defender Adversarial Game for Robust LLM Safety", ICML 2026
• Jianan Li, Simeng Qin, Xiaojun Jia, Lionel Z. WANG, Tianhang Zheng, Xiaoshuang Jia, Yang Liu, Xiaochun Cao, "Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs", ICML 2026
• Jiangwen Dong, Jiayu Li, Tianhang Zheng, Wanyu Lin, "HybridFlow: Resource-Adaptive Subtask Routing for Efficient Edge-Cloud LLM Inference", ICML 2026
• Mengnan Zhao, Lihe Zhang, BoWang, Tianhang Zheng, Hong Zhong, Geyong Min, "Mitigating Error Amplification in Fast Adversarial Training", CVPR 2026
• Qingyu Liu, Yitao Zhang, Zhongjie Ba, Chao Shuai, Peng Cheng, Tianhang Zheng, Zhibo Wang, "Attack-Resistant Watermarking for AIGC Image Forensics via Diffusion-based Semantic Deflection", ICLR 2026
• Hanxi Guo, Hao Wang, Tao Song, Tianhang Zheng, Yang Hua, Haibing Guan, and Xiangyu Zhang, "Poisoning with A Pill: Circumventing Detection in Federated Learning", AAAI 2026
• Weiwei Qi, Shuo Shao, Wei Gu, Tianhang Zheng, Puning Zhao, Zhan Qin, Kui Ren, "MAJIC: Markovian Adaptive Jailbreaking via Iterative Composition of Diverse Innovative Strategies", AAAI 2026
• Xinzhe Huang, Kedong Xiu, Tianhang Zheng, Churui Zeng, Wangze Ni, Zhan Qin, Kui Ren, Chun Chen, "DualBreach: Efficient Dual-Jailbreaking via Target-Driven Initialization and Multi-Target Optimization", NDSS 2026
• Meng Ding, Mingxi Lei, Shaowei Wang, Tianhang Zheng, Di Wang, Jinhui Xu, "Nearly Optimal Differentially Private ReLU Regression", In 41st Conference on Uncertainty in Artificial Intelligence (UAI)
• Puning Zhao, Rongfei Fan, Shaowei Wang, Li Shen, Qixin Zhang, ZongKe, Tianhang Zheng, "Contextual Bandits for Unbounded Context Distributions", In Forty-Second International Conference on Machine Learning (ICML, CCF-A)
• Jia Li, Lijie Hu, Jingfeng Zhang, Tianhang Zheng, Hua Zhang, Di Wang, "Fair Text-to-Image Diffusion via Fair Mapping", In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI, CCF-A)
• Xinyu Zhang, Qingyu Liu, Zhongjie Ba, Yuan Hong, Tianhang Zheng, Feng Lin, Li Lu, Kui Ren, "Fltracer: Accurate poisoning attack provenance in federated learning", In IEEE Transactions on Information Forensics and Security (TIFS, CCF-A)
• Tianhang Zheng, Baochun Li, "CMI: Client-Targeted Membership Inference in Federated Learning", In IEEE Transactions on Dependable and Secure Computing (TDSC, CCF-A)
• Tianhang Zheng, Hao Lan, Baochun Li, "Be Careful with PyPI Packages: You May Unconsciously Spread Backdoor Model Weights", In Proceedings of the 6th Conference on Machine Learning and Systems (MLSys 2023)
• Tianhang Zheng, Baochun Li, "InfoCensor: An Information-Theoretic Framework against Sensitive Attribute Inference and Demographic Disparity", In ACM ASIA Conference on Computer and Communications Security (AsiaCCS 2022) [GitHub]
• Tianhang Zheng, Baochun Li, "Poisoning Attacks on Deep Learning based Wireless Traffic Prediction", In IEEE INFOCOM 2022-IEEE Conference on Computer Communication (INFOCOM 2022, CCF-A)
• Yi Zhu, Chenglin Miao, Tianhang Zheng, Foad Hajiaghajani, Lu Su, Chunming Qiao, "Can We Use Arbitrary Objects to Attack LiDAR Perception in Autonomous Driving?", In ACM Conference on Computer and Communications Security, 2021 (CCS 2021, CCF-A)
• Hengtong Zhang, Tianhang Zheng, Jing Gao, Yaliang Li, Lu Su and Bo Li, "Profanity-Avoiding Training Framework for Seq2seq Models with Certified Robustness", In Empirical Methods in Natural Language Processing, 2021 (EMNLP21)
• Tianhang Zheng, Baochun Li, "First-Order Efficient General-Purpose Clean-Label Data Poisoning", In IEEE INFOCOM 2021-IEEE Conference on Computer Communication (INFOCOM 2021, CCF-A)
• Zhongjie Ba, Tianhang Zheng (co-first author), Xinyu Zhang, Zhan Qin, Baochun Li, Xue Liu, Kui Ren, "Learning-based Practical Smartphone Eavesdropping with Built-in Accelerometer", In Proceedings of the 26th Annual Network and Distributed System Security Symposium (NDSS 2020) (equal contribution)
• Tianhang Zheng, Changyou Chen, Junsong Yuan, Bo Li, and Kui Ren, "PointCloud Saliency Maps", In Proceedings of the IEEE International Conference on Computer Vision, 2019 (ICCV19)
• Hengtong Zhang, Tianhang Zheng, Jing Gao, Chenglin Miao, Lu Su, Yaliang Li, and Kui Ren, "Data poisoning attack against knowledge graph embedding", In Proceedings of the 28th International Joint Conference on Artificial Intelligence, AAAI Press, 2019 (IJCAI19)
• Tianhang Zheng, Changyou Chen, and Kui Ren, "Distributionally adversarial attack", In Proceedings of the AAAI Conference on Artificial Intelligence, 2019 (AAAI 2019)
• Qi Wei, Kai Fan, Wenlin Wang, Tianhang Zheng, Chakraborty Amit, Katherine Heller, Changyou Chen, and Kui Ren, "InverseNet: Solving Inverse Problems of Multimedia Data with Splitting Networks", In 2019 IEEE International Conference on Multimedia and Expo, pp. 1324-1329. IEEE, 2019 (ICME 2019)
• Tianhang Zheng, Zhi Sun, and Kui Ren, "FID: Function Modeling-based Data-Independent and Channel-Robust Physical-Layer Identification", In IEEE INFOCOM 2019-IEEE Conference on Computer Communications (INFOCOM 2019)

Contact

📧 Email: zthzheng@zju.edu.cn

📍 Address: 浙江大学科创水博园 B06 405