Yuntao Du (杜云滔)

Data Privacy & Trustworthy Machine Learning

yuntao.png

I am a PhD student in computer science at Purdue University, advised by Prof. Ninghui Li. My research interests lie in Data Privacy and Privacy in Machine Learning. I am also broadly interested in analyzing emerging privacy and security risks arising from recent advances in AI. Here is my CV.

My research has been recognized and supported by the Ross Fellowship (2023-2027), Presidential Doctoral Excellence Awards (2023-2027), and Herbold Scholarship (2023-2024).

News

Jan 27, 2026 Three of papers on membership inference, focusing on new shadow training paradigm, LLM tokenization, and LLM fine-tuning, have been accepted to USENIX Security 2026.
Sep 9, 2025 We present a comprehensive study on the emerging privacy risks of LLMs beyond data privacy, which has been published at Bulletin of the Technical Committee on Data Engineering.
Aug 31, 2025 We present a new class of MIA for jointly membership inference, which will be presented at NDSS 2026.
May 7, 2025 We present a new privacy threat to online pseudonymity with Language Model Agents.

Selected Publications

  1. COLM
    AutoProfiler.png
    Automated Profile Inference with Language Model Agents
    Yuntao Du, Zitao Li, Bolin Ding, Yaliang Li, Hanshen Xiao, Jingren Zhou, and Ninghui Li
    In COLM 2025 Workshop on AI Agents: Capabilities and Safety, 2025
    arXiv Code
  2. USENIX Security
    IMIA.png
    Imitative Membership Inference Attack
    Yuntao Du, Yuetian Chen, Hanshen Xiao, Bruno Ribeiro, and Ninghui Li
    2026
    arXiv Code
  3. NDSS
    NDSS26_CPMIA.png
    Cascading and Proxy Membership Inference Attacks
    Yuntao Du, Jiacheng Li, Yuetian Chen, Kaiyuan Zhang, Zhizhen Yuan, Hanshen Xiao, Bruno Ribeiro, and Ninghui Li
    In Network and Distributed System Security Symposium (NDSS), 2026
    arXiv Blog Code
  4. CCS
    CCS25_SynMeter.png
    Systematic Assessment of Tabular Data Synthesis
    Yuntao Du, and Ninghui Li
    In ACM Conference on Computer and Communications Security (CCS), 2025
    arXiv Blog Code
  5. Data Eng. Bulletin
    Bulletin_positionllm.png
    Beyond Data Privacy: New Privacy Risks for Large Language Models
    Yuntao Du, Zitao Li, Ninghui Li, and Bolin Ding
    IEEE Data Engineering Bulletin, 2025
    arXiv

Selected Honors & Awards

• Ross Fellowship, Purdue University, 2023
• Herbold Scholarship, Purdue University, 2023
• Presidential Doctoral Excellence Awards, Purdue University, 2023
• Excellent Masters Dissertation, Chinese Institute of Electronic, 2023
• National Scholarship, China, 2022-2023

Professional Services

Conference Reviewer
• International Conference on Learning Representations (ICLR): 2025 - 2026.
• International Conference on Artificial Intelligence and Statistics (AISTATS): 2025 - 2026.
• The AAAI Conference on Artificial Intelligence (AAAI): 2023 - 2026.
• ACM Web Conference (WWW): 2026.
• International Conference on Web Search and Data Mining (WSDM): 2026.
• ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR): 2023 - 2025.
• ACM International Conference on Information and Knowledge Management (CIKM): 2024 - 2025.
• International Joint Conference on Neural Networks (IJCNN): 2025.
• Table Representation Learning Workshop (TRL): 2024 - 2025.
• International ACM SIGIR Conference on Information Retrieval in the Asia Pacific (SIGIR-AP): 2023 - 2025.
Journal Reviewer
• ACM Computing Surveys (CSUR)
• ACM Transactions on Privacy and Security (TOPS)
• IEEE Transactions on Knowledge and Data Engineering (TKDE)
• ACM Transactions on Recommender Systems (TORS)