Yuntao Du (杜云滔)

Publications

The complete publication list can be found on Google Scholar. Also browse publications by topic.
^* equal contribution, ^† mentored student

2026

1. Privacy Leakage from a Thousand Words: Millipixel Location Recovery from Dot Maps
   Yuntao Du^*, Tanishq Pauskar^*†, Hao Wang, Jing Su, Ninghui Li
   ACM CCS 2026  [pdf]  [code]
   Data Privacy First to achieve 1-meter attack accuracy in location recovery from national-scale dot maps.
   Our findings have been adopted by map visualization platforms (e.g., QGIS) to warn users of these risks, and we are working with the U.S. CDC to revise its cartographic guidelines.
2. A Preliminary Study of LLM Distillation Inference
   Edward Chen^†, Yuntao Du
   ACM CCS 2026 (Poster)
3. Automated Profile Inference with Language Model Agents
   Yuntao Du, Zitao Li, Bolin Ding, Yaliang Li, Hanshen Xiao, Jingren Zhou, Ninghui Li
   ACL 2026 (Findings)  [pdf]  [code]
   AI Security & Safety First study showing that LLM agents enable automated doxing at web scale.
4. AutoVerifier: An Agentic Automated Verification Framework Using Large Language Models
   Yuntao Du, Minh Dinh, Kaiyuan Zhang, Ninghui Li
   arXiv preprint 2026  [pdf]  [code]
   AI Security & Safety Six-layer LLM-agent framework for evidence-backed technical claim verification.
5. Cascading and Proxy Membership Inference Attacks
   Yuntao Du, Jiacheng Li, Yuetian Chen, Kaiyuan Zhang, Zhizhen Yuan, Hanshen Xiao, Bruno Ribeiro, Ninghui Li
   NDSS 2026  [pdf]  [code]  [blog]
   Machine Learning Privacy Formulates and categorizes MIAs and first exploits membership dependencies.
6. Imitative Membership Inference Attack
   Yuntao Du, Yuetian Chen, Hanshen Xiao, Bruno Ribeiro, Ninghui Li
   USENIX Security 2026  [pdf]  [code]  [blog]
   Machine Learning Privacy A new shadow training paradigm for MIAs with significantly reduced computation.
7. Membership Inference Attacks on Tokenizers of Large Language Models
   Meng Tong^*†, Yuntao Du^*, Kejiang Chen, Weiming Zhang, Ninghui Li
   USENIX Security 2026  [pdf]  [code]
   Machine Learning Privacy First study showing the privacy risk of LLM tokenizers.
8. Window-based Membership Inference Attacks Against Fine-tuned Large Language Models
   Yuetian Chen, Yuntao Du, Kaiyuan Zhang, Ashish Kundu, Charles Fleming, Bruno Ribeiro, Ninghui Li
   USENIX Security 2026  [pdf]  [code]
9. Membership Inference Attacks Against Fine-tuned Diffusion-Based Language Models
   Yuetian Chen, Kaiyuan Zhang, Yuntao Du, Edoardo Stoppa, Charles Fleming, Ashish Kundu, Bruno Ribeiro, Ninghui Li
   ICLR 2026  [pdf]  [code]

2025

1. Systematic Assessment of Tabular Data Synthesis
   Yuntao Du, Ninghui Li
   ACM CCS 2025  [pdf]  [code]  [blog]
   Data Privacy Proposes a unified evaluation framework for tabular data synthesis algorithms.
2. Beyond Data Privacy: New Privacy Risks for Large Language Models
   Yuntao Du, Zitao Li, Ninghui Li, Bolin Ding
   IEEE Data Eng. Bulletin 2025  [pdf]
   AI Security & Safety Systematizes new privacy risks of LLM agents beyond training-data leakage.
3. SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks
   Kaiyuan Zhang, Siyuan Cheng, Hanxi Guo, Yuetian Chen, Zian Su, Shengwei An, Yuntao Du, Charles Fleming, Ashish Kundu, Xiangyu Zhang, Ninghui Li
   USENIX Security 2025  [pdf]  [code]

2024

1. Real-Time Trajectory Synthesis with Local Differential Privacy
   Yujia Hu^†, Yuntao Du, Zhikun Zhang, Ziquan Fang, Lu Chen, Kai Zheng, Yunjun Gao
   IEEE ICDE 2024  [pdf]  [code]

2023

1. LDPTrace: Locally Differentially Private Trajectory Synthesis
   Yuntao Du, Yujia Hu^†, Zhikun Zhang, Ziquan Fang, Lu Chen, Baihua Zheng, Yunjun Gao
   VLDB 2023  [pdf]  [code]  [blog]
2. Towards Explainable Collaborative Filtering with Taste Clusters Learning
   Yuntao Du, Jianxun Lian, Jing Yao, Xiting Wang, Mingqi Wu, Lu Chen, Yunjun Gao, Xing Xie
   WWW 2023  [pdf]  [code]
3. MetaKG: Meta-learning on Knowledge Graph for Cold-start Recommendation
   Yuntao Du, Xinjun Zhu^†, Lu Chen, Ziquan Fang, Yunjun Gao
   IEEE TKDE 2023  [pdf]  [code]
4. Knowledge-refined Denoising Network for Robust Recommendation
   Xinjun Zhu^†, Yuntao Du, Lu Chen, Baihua Zheng, Yunjun Gao
   ACM SIGIR 2023  [pdf]  [code]
5. FLBooster: A Unified and Efficient Platform for Federated Learning Acceleration
   Zhihao Zeng^†, Yuntao Du, Ziquan Fang, Lu Chen, Shiliang Pu, Guodong Chen, Hui Wang, Yunjun Gao
   IEEE ICDE 2023  [pdf]

2022

1. HAKG: Hierarchy-Aware Knowledge Gated Network for Recommendation
   Yuntao Du, Xinjun Zhu^†, Lu Chen, Baihua Zheng, Yunjun Gao
   ACM SIGIR 2022  [pdf]  [code]
2. Self-Guided Learning to Denoise for Robust Recommendation
   Yunjun Gao, Yuntao Du, Yujia Hu, Lu Chen, Xinjun Zhu, Ziquan Fang, Baihua Zheng
   ACM SIGIR 2022  [pdf]  [code]
3. Spatio-Temporal Trajectory Similarity Learning in Road Networks
   Ziquan Fang, Yuntao Du, Xinjun Zhu, Danlei Hu, Lu Chen, Yunjun Gao, Christian S. Jensen
   ACM KDD 2022  [pdf]  [code]

2021

1. E2DTC: An End to End Deep Trajectory Clustering Framework via Self-Training
   Ziquan Fang, Yuntao Du, Lu Chen, Yujia Hu, Yunjun Gao, Gang Chen
   IEEE ICDE 2021  [pdf]  [code]
2. MDTP: A Multi-source Deep Traffic Prediction Framework over Spatio-Temporal Trajectory Data
   Ziquan Fang, Lu Pan, Lu Chen, Yuntao Du, Yunjun Gao
   VLDB 2021  [pdf]