Tian Dong (董天)

Tian Dong (董天)

I am currently a Postdoctoral Fellow at Hong Kong University with Prof. Hao Chen, working on AI security & privacy and the application of AI to security problems. Previously, I obtained my PhD in Computer Science (2025) from the NSEC Lab at Shanghai Jiao Tong University (SJTU), advised by Prof. Haojin Zhu, where my research centered on model and dataset provenance in the era of large language models. I hold a master’s degree from SJTU (2022) and the Diplôme d’ingénieur (X17) from École Polytechnique, where my thesis explored robust federated learning for intrusion detection. Broadly, my research interests lie at the intersection of security, privacy, and machine learning.

Selected Publications

  1. [Security’25] Depth Gives a False Sense of Privacy: LLM Internal States Inversion
    Tian Dong, Yan Meng, Shaofeng Li, Guoxing Chen, Zhen Liu, Haojin Zhu.
    USENIX Security, 2025.

  2. [NDSS’25] The Philosopher’s Stone: Trojaning Plugins of Large Language Models
    Tian Dong, Minhui Xue, Guoxing Chen, Rayne Holland, Shaofeng Li, Yan Meng, Zhen Liu, Haojin Zhu.
    Network and Distributed System Security Symposium, 2025. [pdf]

  3. [ICCC’24] BrInstFlip: A Universal Tool for Attacking DNN-Based Power Line Fault Detection Models
    Yixin Jiang, Yanbo Xu, Zhihong Liang, Wenqian Xu, Tian Dong, Ximing Zhang, Yiwei Yang, Yan Meng and Haojin Zhu.
    IEEE/CIC International Conference on Communications in China, 2024. Best Paper Award

  4. [S&P’24] Learn what you want to unlearn: Unlearning inversion attacks against machine unlearning
    Hongsheng Hu, Shuo Wang, Tian Dong, Minhui Xue.
    IEEE Symposium on Security and Privacy, 2024. [pdf]

  5. [ESEC/FSE’23] Mate! Are you really aware? An explainability-guided testing framework for robustness of malware detectors
    Ruoxi Sun, Minhui Xue, Gareth Tyson, Tian Dong, Shaofeng Li, Shuo Wang, Haojin Zhu, Seyit Camtepe, Surya Nepal.
    ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2023. [pdf] Distinguished Paper Award

  6. [INFOCOM’23] Mind Your Heart: Stealthy Backdoor Attack on Dynamic Deep Neural Network in Edge Computing
    Tian Dong, Ziyuan Zhang, Han Qiu, Tianwei Zhang, Hewu Li and Terry Wang.
    IEEE International Conference on Computer Communications, 2023. [pdf]

  7. [NDSS’23] $\text{RAI}^2$: Responsible Identity Audit Governing the Artificial Intelligence
    Tian Dong, Shaofeng Li, Guoxing Chen, Minhui Xue, Haojin Zhu and Zhen Liu.
    Network and Distributed System Security Symposium, 2023. [pdf]

  8. [IEEE S&P Magazine] Backdoors Against Natural Language Processing: A Review
    Shaofeng Li, Tian Dong, Benjamin Zi Hao Zhao, Minhui Xue, Suguo Du and Haojin Zhu.
    IEEE Security & Privacy, 2022. [pdf]

  9. [ICML’22] Privacy for Free: How does Dataset Condensation Help Privacy?
    Tian Dong, Bo Zhao, and Lingjuan Lyu.
    The 39th International Conference on Machine Learning, Baltimore, Maryland, USA, 2022. [pdf] Outstanding Paper Award

  10. [ISPA’21] Towards Fast Network Intrusion Detection based on Efficiency-preserving Federated Learning
    Tian Dong, Han Qiu, Jialiang Lu, Meikang Qiu, and Chun Fan.
    IEEE International Symposium on Parallel and Distributed Processing with Applications, Virtual Conference, Oct. 2021. [pdf]

  11. [CCS’21] Hidden Backdoors in Human-Centric Language Models
    Shaofeng Li, Hui Liu, Tian Dong, Benjamin Zi Hao Zhao, Minhui Xue, Haojin Zhu and Jialiang Lu.
    ACM Conference on Computer and Communications Security, Virtual Conference, Nov. 2021. [pdf] Best Paper Award (Runner-Ups)

  12. [IoT-J] Adversarial Attacks against Network Intrusion Detection in IoT Systems
    Han Qiu, Tian Dong, Tianwei Zhang, Jialiang Lu, Gerard Memmi, and Meikang Qiu.
    IEEE Internet of Things Journal, Dec. 2020. [pdf]

Awards & Honor

Young Elite Scientists Sponsorship (PhD Program) , 2025

Internet Society Fellowship, NDSS 2025

IEEE/CIC ICCC 2024 Best Paper Award, 2024

Bytedance scholarship, 2023

National Scholarship, 2023

ACM SIGSOFT Distinguished Paper Award, 2023

ICML 2022 Outstanding Paper Award, 2022

ACM CCS 2021 Best Paper Award Runner-up, 2021

Services

  • Conference Reviewer: ICML, NeurIPS, ICLR, CVPR, ECCV, ICCV, WWW, USENIX Security Artifact Evaluation, ACM CCS Artifact Evaluation, ICCC

  • External Reviewer: IEEE S&P, ACM CCS, USENIX Security, NDSS

  • Journal Reviewer: TDSC, TIFS, TOPS, TWC, PPNA, IoT-J

Last updated: 2025/06.