I am an assistant professor at University of Missouri (Kansas City Campus). I received my Ph.D. degree from University of Toronto, M.S. degree from University at Buffalo, and B.Eng. degree from Peking University. My research interests lie in the interaction between machine learning, security, and privacy. Given my interdisciplinary education background, I am also interested in AI4Science

I am actively looking for self-motivated students to work with me. Our group welcomes K-12 students and undergraduate students from underrepresented groups, and we collect some materials about cutting-edge AI techniques to help you understand AI. You can find the materials at “cutting-edge AI techniques”

News

Our paper (first-authored) “Differentially Private Dataset Condensation” was accepted to NDSS AISCC 2024.

Stay Tuned: I am establishing two Git repositories for research and practice on distributed machine learning and large language models. Note that they can only be used for non-profit research or practice.

I am grateful for receiving the FFE award from UMKC to support our research on AI + Health.

I will serve as the Associate Editor for IEEE Transactions on Circuits and Systems for Video Technology starting from 2024.

Our paper (first-authored) “CMI: Client-Targeted Membership Inference in Federated Learning” was accepted to TDSC.

I am grateful for receiving funding support from Division of Diversity and Inclusion (UMKC) to work on promoting fairness in machine learning.

Our paper (first-authored) “RDM-DC: Poisoning Resilient Dataset Condensation with Robust Distribution Matching” was accepted to UAI 2023

Our paper (first-authored) “Be Careful with PyPI Packages: You May Unconsciously Spread Backdoor Model Weights” was accepted to MLSys 2023

Selected Publications

Privacy Meets Deep Learning

Tianhang Zheng, Baochun Li, “CMI: Client-Targeted Membership Inference in Federated Learning” In IEEE Transactions on Dependable and Secure Computing (TDSC)

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

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)

Poisoning Attacks and Defenses

Tianhang Zheng, Baochun Li. “RDM-DC: Poisoning Resilient Dataset Condensation with Robust Distribution Matching” In Uncertainty in Artificial Intelligence, pp. 2541-2550. PMLR, 2023 (UAI 2023)

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) (MLSys 2023)

Tianhang Zheng, Baochun Li “Poisoning Attacks on Deep Learning based Wireless Traffic Prediction” In IEEE INFOCOM 2022-IEEE Conference on Computer Communication (INFOCOM 2022)

Tianhang Zheng, Baochun Li “First-Order Efficient General-Purpose Clean-Label Data Poisoning” In IEEE INFOCOM 2021-IEEE Conference on Computer Communication (INFOCOM 2021)

Adversarial Attacks and Defenses

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)

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)

Tianhang Zheng, Changyou Chen, and Kui Ren. “Distributionally adversarial attack” In Proceedings of the AAAI Conference on Artificial Intelligence, 2019 (AAAI 2019)