Publications

Below are selected publications. * indicates I am the corresponding author. Underline indicates my students, post-doc or intern.

Selected Journal Papers

• Wei Dong, Juanru Fang, Ke Yi, Yuchao Tao, Ashwin Machanavajjhala. “Instance-optimal Truncation for Differentially Private Query Evaluation with Foreign Keys.” TODS, 49(4):13, Nov 2024. [PDF]
• Wei Dong, Ke Yi. “Query Evaluation under Differential Privacy.” SIGMOD Rec., 52(3): 6-17, Nov 2023. [PDF]

Selected Conference Papers

Data Privacy and Security

• Huizhong Wang, Yuanyuan Zeng, Kun Chen, Wei Dong, Chenhao Ma. “Scalable Privacy-Preserving Shortest Path Distance Computation via 2-Hop Labeling in MPC.” SIGMOD, May 2026.
• Xinghe Chen, Dajun Sun, Quanqing Xu, Wei Dong*. “A General Framework for Per-record Differential Privacy.” SIGMOD, May 2026. [PDF]
• Yihua Hu, Hao Ding, Wei Dong*. “N2E: A General Framework to Reduce Node-Differential Privacy to Edge-Differential Privacy for Graph Analytics.” SIGMOD, May 2026. [PDF]
• Siyi Wang, Qiyao Luo, Yihua Hu, Lixu Wang, Quanqing Xu, Chuanhui Yang, Zhan Qin, Kui Ren, Wei Dong*. “Defense against Poisoning Attacks under Shuffle-DP.” SIGMOD, May 2026.
• Yihua Hu, Kuncan Wang, Wei Dong*. “Acyclic Graph Pattern Counting under Local Differential Privacy.” SIGMOD, May 2026.
• Zhiang Wu, Wei Dong, Xiao Hu. “Differentially Oblivious Multi-way Joins.” SIGMOD, May 2026.
• Dajun Sun, Wei Dong*, Yuan Qiu, Ke Yi, Graham Cormode. "Sum Estimation under Personalized Local Differential Privacy." NeurIPS, Sep 2025. [PDF]
• Qiyao Luo, Jianzhe Yu, Wei Dong*, Quanqing Xu, Chuanhui Yang, Ke Yi. "RM²: Answer Counting Queries Efficiently under Shuffle Differential Privacy." SIGMOD, Jun 2025. [PDF] [Code]
• Dajun Sun, Wei Dong*, Yuan Qiu, Ke Yi. “Personalized Truncation for Personalized Privacy.” SIGMOD, Jun 2025. [PDF]
• Wei Dong, Qiyao Luo, Giulia Fanti, Elaine Shi, Ke Yi. “Almost Instance-optimal Clipping for Summation Problems in the Shuffle Model of Differential Privacy.” CCS, Oct 2024. [PDF] [Full Version]
• Dajun Sun, Wei Dong, Ke Yi. "Confidence Intervals for Private Query Processing." VLDB, Aug 2024. [PDF] [Full Version]
• Wei Dong, Zijun Chen, Qiyao Luo, Elaine Shi, Ke Yi. “Continual Observation of Joins under Differential Privacy.” SIGMOD, Jun 2024. [PDF]
• Wei Dong, Dajun Sun, Ke Yi. “Better than Composition: How to Answer Multiple Relational Queries under Differential Privacy.” SIGMOD, Jun 2023. [PDF] [Code]
• Wei Dong, Ke Yi. “Universal Private Estimators.” PODS, Jun 2023. [PDF] [Full Version]
• Wei Dong, Qiyao Luo, Ke Yi. "Continual Observation under User-level Differential Privacy." S&P, May 2023. [PDF]
• Wei Dong, Yuting Liang, Ke Yi. "Differentially Private Covariance Revisited." NeurIPS, Nov 2022. [PDF] [Full Version] [Code]
• Juanru Fang, Wei Dong, Ke Yi. "Shifted Inverse: A General Mechanism for Monotonic Functions under User Differential Privacy." CCS, Nov 2022. [PDF] [Code]
• Wei Dong, Juanru Fang, Ke Yi, Yuchao Tao, Ashwin Machanavajjhala. “R2T: Instance-optimal Truncation for Differentially Private Query Evaluation with Foreign Keys.” SIGMOD, Jun 2022. [PDF] [Full Version] [Code] (Best Paper)
• Wei Dong, Ke Yi. “A Nearly Instance-optimal Differentially Private Mechanism for Conjunctive Queries.” PODS, Jun 2022. [PDF] [Code]
• Wei Dong, Ke Yi. “Residual Sensitivity for Differentially Private Multi-Way Joins.” SIGMOD, Jun 2021. [PDF] [Full Version] [Code]

LLM and AI Security

• Xinyun Zhou, Xinfeng Li, Yinan Peng, Ming Xu, Xuanwang Zhang, Miao Yu, Yidong Wang, Xiaojun Jia, Kun Wang, Qingsong Wen, XiaoFeng Wang, Wei Dong. "Evaluating RAG Robustness to Symbolic Perturbations" SIGKDD, August 2026. [PDF]
• Xinfeng Li, Tianze Qiu, Yingbin Jin, Lixu Wang, Hanqing Guo, Xiaojun Jia, XiaoFeng Wang, Wei Dong*. "WebCloak: Characterizing and Mitigating Threats from LLM-Driven Web Agents as Intelligent Scrapers." S&P, May 2026. [PDF]
• Feiran Liu, Yuzhe Zhang, Xinyi Huang, Yinan Peng, Xinfeng Li, Lixu Wang, Yutong Shen, Ranjie Duan, Simeng Qin, Xiaojun Jia, Qingsong Wen, Wei Dong. "The Eye of Sherlock Holmes: Uncovering User Private Attribute Profiling via Vision-Language Model Agentic Framework." ACM MM, Oct 2025. [PDF]
• Lixu Wang, Chenxi Liu, Junfeng Guo, Qingqing Ye, Heng Huang, Haibo Hu, Wei Dong*. “Federated Continuous Category Discovery and Learning.” ICCV, Oct 2025. [PDF]