Yangfan Jiang 「姜洋帆」

Short Bio: I am a Ph.D. candidate in Computer Science at the National University of Singapore, advised by Prof. Xiaokui Xiao. I received my B.Eng. degree in Computer Science from Sun Yat-sen University, advised by Prof. Di Wu.

Research: My research focuses on privacy and security for AI and data analytics. I develop practical algorithms for training and using LLMs over sensitive data with formal, task-aligned privacy guarantees.

Contact: jyangfan@u.nus.edu

[CV] [Google Scholar]

Publications

AI Privacy and Security

1. Private Direct Preference Optimization for LLM Alignment
   Yangfan Jiang, Fei Wei, Ergute Bao, Xiaokui Xiao, Yaliang Li, and Bolin Ding
   In ACM SIGSAC Conference on Computer and Communications Security (CCS), 2026.


2. Accurate Table Question Answering with Accessible LLMs
   Yangfan Jiang, Fei Wei, Ergute Bao, Yaliang Li, Bolin Ding, Yin Yang, and Xiaokui Xiao
   In IEEE International Conference on Data Engineering (ICDE), 2026.


3. Calibrating Noise for Group Privacy in Subsampled Mechanisms
   Yangfan Jiang, Xinjian Luo, Yin Yang, and Xiaokui Xiao
   In International Conference on Very Large Data Bases (VLDB), 2025.


4. Unlocking the Power of Differentially Private Zeroth-Order Optimization for Fine-Tuning LLMs
   Ergute Bao, Yangfan Jiang, Fei Wei, Xiaokui Xiao, Zitao Li, Yaliang Li, and Bolin Ding
   In USENIX Security Symposium (USENIX Security), 2025.


5. Passive Inference Attacks on Split Learning via Adversarial Regularization
   Xiaochen Zhu, Xinjian Luo, Yuncheng Wu, Yangfan Jiang, Xiaokui Xiao, and Beng Chin Ooi
   In Network and Distributed System Security Symposium (NDSS), 2025.


6. Protecting Label Distribution in Cross-Silo Federated Learning
   Yangfan Jiang, Xinjian Luo, Yuncheng Wu, Xiaokui Xiao, and Beng Chin Ooi
   In IEEE Symposium on Security and Privacy (S&P), 2024.


7. On Data Distribution Leakage in Cross-Silo Federated Learning
   Yangfan Jiang, Xinjian Luo, Yuncheng Wu, Xiaochen Zhu, Xiaokui Xiao, and Beng Chin Ooi
   IEEE Transactions on Knowledge and Data Engineering (TKDE), 36(7): 3312-3328, 2024.


8. Exploring Privacy and Fairness Risks in Sharing Diffusion Models: An Adversarial Perspective
   Xinjian Luo, Yangfan Jiang, Fei Wei, Yuncheng Wu, Xiaokui Xiao, and Beng Chin Ooi
   IEEE Transactions on Information Forensics and Security (TIFS), 19: 8109-8124, 2024.


9. Feature Inference Attack on Shapley Values
   Xinjian Luo, Yangfan Jiang, and Xiaokui Xiao
   In ACM SIGSAC Conference on Computer and Communications Security (CCS), 2022.

Reliable Data Analytics

1. Benchmarking Text-to-SQL under Role-Based Access Control
   Yang Fei, Yangfan Jiang, Yin Yang, and Xiaokui Xiao
   In ACM SIGMOD International Conference on Management of Data (SIGMOD), 2027.


2. Fair Data Pre-Processing with Imperfect Attribute Space
   Ying Zheng, Yangfan Jiang, and Kian-Lee Tan
   In ACM SIGMOD International Conference on Management of Data (SIGMOD), 2026.


3. CausalPre: Scalable and Effective Data Pre-Processing for Causal Fairness
   Ying Zheng, Yangfan Jiang, and Kian-Lee Tan
   In IEEE International Conference on Data Engineering (ICDE), 2026.


4. On the Detection of Shilling Attacks in Federated Collaborative Filtering
   Yangfan Jiang, Yipeng Zhou, Di Wu, Chao Li, and Yan Wang
   In IEEE International Symposium on Reliable Distributed Systems (SRDS), 2020.


5. Robust Size Estimation of Online Social Networks via Subgraph Sampling
   Yangfan Jiang, Yao Fu, Yipeng Zhou, and Di Wu
   IEEE Transactions on Network Science and Engineering (TNSE), 7(4): 2702-2713, 2020.

Academic Services

• ACM The Web Conference (WWW): 2026
• ACM International Conference on Information and Knowledge Management (CIKM): 2024 - 2026

• IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
• IEEE Transactions on Dependable and Secure Computing (TDSC)
• IEEE Transactions on Information Forensics and Security (TIFS)
• IEEE Transactions on Knowledge and Data Engineering (TKDE)