I am currently a Postdoctoral Associate in the Department of Biomedical Informatics & Data Science at Yale School of Medicine, working with Prof. Lucila Ohno-Machado. Previously, I was a postdoctoral fellow in Assured Information Management and Sharing (AIMS) at the Computer Science Department of Emory University, supervised by Prof. Li Xiong. I received my Ph.D. from the School of Information, Renmin University of China, under the supervision of Prof. Hong Chen. During my Ph.D. study, I was a research intern at Amazon AWS AI Lab and Microsoft Research Asia. I earned my Bachelor’s degree from China University of Petroleum, during which I was a visiting student at the University of Calgary.

My research focuses on privacy-preserving machine learning, with an emphasis on differential privacy, federated learning, and privacy risks in large language models. I work on both auditing privacy risks and developing defenses that deliver privacy guarantees while remaining efficient, inclusive, and practically deployable. My recent focuses include:

• Trustworthy LLMs & Foundation Models: Auditing emerging privacy risks (S&P’26, CCS’24); preventing privacy leakage and unauthorized exploitation (NDSS’26, ACL’25).
• Differentially Private Optimization: Designing hyperparameter-free and utility-aware DP algorithms for general-purpose training (ICLR’25, ACM MM’25).
• Privacy-Preserving Federated Learning: Building private, efficient, and inclusive FL systems across heterogeneous devices (SIGKDD’23, SIGKDD’22, AAAI’21).

🔥 News

📝 Publications ()

† represents co-first author, * represents corresponding author. See full list here

Conference Papers

SnapAudit: Active Auditing of Differentially Private In-Context Learning via Snapshot-Based Simulation
Yuyang Xia, Ruixuan Liu*, Li Xiong
Conference on Neural Information Processing Systems (NeurIPS), to appear

Direct Token Optimization: A Self-Contained Approach to Large Language Model Unlearning
Hongkyu Lee, Ruixuan Liu*, Li Xiong
Proceedings of the Findings of the 64th Association for Computational Linguistics (ACL Findings)

Beyond Indistinguishability: Measuring Extraction Risk in LLM APIs
Ruixuan Liu, David Evans, Li Xiong
Proceedings of the 47th IEEE Symposium on Security and Privacy (S&P, Acceptance Rate: 13%)

ExpShield: Safeguarding Web Text from Unauthorized Crawling and LLM Exploitation
Ruixuan Liu, Toan Tran, Tianhao Wang, Hongsheng Hu, Shuo Wang, Li Xiong
Proceedings of the 33rd Network and Distributed System Security Symposium (NDSS, Acceptance Rate: 152/950=16%)

Zero Redundancy Distributed Learning with Differential Privacy
Zhiqi Bu, Justin Chiu, Ruixuan Liu, Sheng Zha, George Karypis
Proceedings of Machine Learning and Systems (MLSys)

Differentially Private Visual Learning with Public Subspace Augmented by Synthetic Data
Haichao Sha, Yuncheng Wu, Ruixuan Liu, Yang Cao, Hong Chen
Proceedings of the 33rd ACM International Conference on Multimedia (ACM MM, Outstanding Paper Award)

Tokens for Learning, Tokens for Unlearning: Mitigating Membership Inference Attacks in Large Language Models via Dual-Purpose Training
Toan Tran, Ruixuan Liu*, Li Xiong
Proceedings of the Findings of the 63rd Association for Computational Linguistics (ACL Findings)

Towards hyperparameter-free optimization with differential privacy
Ruixuan Liu†, Zhiqi Bu†
Proceedings of the 13th International Conference on Learning Representations (ICLR Spotlight, Top 5.1%)

PreCurious: How Innocent Pre-Trained Language Models Turn into Privacy Traps
Ruixuan Liu, Tianhao Wang, Yang Cao, Li Xiong
Proceedings of the 31th ACM Conference on Computer and Communications Security (CCS)

Patient-Centered and Practical Privacy to Support AI for Healthcare
Ruixuan Liu, Hong Kyu Lee, Sivasubramanium V. Bhavani, Xiaoqian Jiang, Lucila Ohno-Machado, Li Xiong
Proceedings of the 6th IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA)

Supporting Pandemic Preparedness with Privacy Enhancing Technology
Ruixuan Liu, Sepanta Zeighami, Haowen Lin, Cyrus Shahabi, Yang Cao, Shun Takagi, Yoko Konishi, Masatoshi Yoshikawa, Li Xiong
Proceedings of the 5th IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA)

PrivateRec: Differentially Private Model Training and Online Serving for Federated News Recommendation
Ruixuan Liu, Yang Cao, Yanlin Wang, Lingjuan Lyu, Yun Chen, Hong Chen
Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (SIGKDD)

No one left behind: Inclusive federated learning over heterogeneous devices
Ruixuan Liu, Fangzhao Wu, Chuhan Wu, Yanlin Wang, Lingjuan Lyu, Hong Chen, Xing Xie
Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (SIGKDD)

Flame: Differentially private federated learning in the shuffle model
Ruixuan Liu, Yang Cao, Hong Chen, Ruoyang Guo, Masatoshi Yoshikawa
Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI)

Efficient-FedRec: Efficient federated learning framework for privacy-preserving news recommendation
Jingwei Yi, Fangzhao Wu, Chuhan Wu, Ruixuan Liu, Guangzhong Sun, Xing Xie
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Fedsel: Federated sgd under local differential privacy with top-k dimension selection
Ruixuan Liu, Yang Cao, Masatoshi Yoshikawa, Hong Chen
Proceedings of 25th International Conference of Database Systems for Advanced Applications (DASFAA)

Mixgeo: Efficient secure range queries on encrypted dense spatial data in the cloud
Ruoyang Guo, Bo Qin, Yuncheng Wu, Ruixuan Liu, Hong Chen, Cuiping Li
Proceedings of the 27th IEEE/ACM International Symposium on Quality of Service (IWQoS)

Journal Papers

DP2-RAG: An Efficient Full-Process Differential Privacy Implementation in Retrieval-Augmented Generation
Yuxuan Cai, Chaoxiang He, Hongsheng Hu, Ruixuan Liu, Bin Benjamin Zhu, Dongmei Zhang, Cheng Hong, Zhicong Huang, Shifeng Sun, Shuo Wang, Dawu Gu
IEEE Transactions on Information Forensics and Security (TIFS)

TransFed: Cross-domain Feature Alignment for Semi-supervised Federated Transfer Learning
Linghui Zeng, Ruixuan Liu, Li Xiong, Joyce C. Ho
Machine Learning (ECML-PKDD 2025 Journal Track)

LuxGeo: Efficient and Security-Enhanced Geometric Range Queries
Ruoyang Guo, Bo Qin, Yuncheng Wu, Ruixuan Liu, Hong Chen, Cuiping Li
IEEE Transactions on Knowledge and Data Engineering (TKDE)

Survey on Privacy Attacks and Defenses in Machine Learning
Ruixuan Liu, Hong Chen, Ruoyang Guo, Dan Zhao, Wenjuan Liang, Cuiping Li
Journal of Software (Chinese)

A pufferfish privacy mechanism for monitoring web browsing behavior under temporal correlations
Wenjuan Liang, Hong Chen, Ruixuan Liu, Yuncheng Wu, Cuiping Li
Computers & Security

🎖 Honors and Awards

• 2nd Prize, CAMDA 2026 (ELSA Health Privacy Challenge, Red Team Track) @ ISMB, 2026
• ELSA Travel Fellowship, ELSA Health Privacy Challenge @ CAMDA, 2026
• Outstanding Paper in Generation Theme, ACM MM, 2025
• Spotlight Paper, ICLR, 2025
• Travel Award, ICLR, 2025
• Commendable Reviewers, SIGKDD, 2025
• Travel Award, ACM CCS Diversity, Equity, and Inclusion (DEI) Workshop, 2024
• Outstanding Doctoral Graduate, Renmin University of China, 2023
• 2nd Prize of CIKM 2022 AnalytiCup Competition (with 3,000 USD), 2022
• 1st-Class Academic Scholarship, School of Information, Renmin University of China, 2019-2022
• Outstanding Visiting Student of University of Calgary, 2018
• Outstanding Undergraduate Scholarship of China Scholarship Council, 2017
• 1st Prize of Software Design Competition of Shandong Province, 2017
• Special Prize of Bochuang Cup National College Students Embedded System Design Competition, 2017
• Excellent Student Leader of Shandong Province, 2017
• Shengli Scholarship of China University of Petroleum, 2017
• Simei Star of China University of Petroleum, 2017
• National Scholarship, Chinese Ministry of Education, 2016

💻 Services

• Journal Reviewer
  • IEEE Transactions on Mobile Computing (TMC) 2024
  • IEEE Transactions on Information Forensics & Security (TIFS) 2024-2026
  • IEEE Transactions on Dependable and Secure Computing (TDSC) 2023-2026
  • IEEE Transactions on Big Data (TBD) 2024
• Conference Program Committee Member
  • ACM Conference on Computer and Communications Security (CCS) 2026
  • IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) 2025-2027
  • AAAI Conference on Artificial Intelligence (AAAI) 2023-2026
  • ACM International Conference on Information and Knowledge Management (CIKM) 2024
• Conference Reviewer
  • IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026
  • ACM Knowledge Discovery and Data Mining (SIGKDD) 2024-2026
  • KDD-Workshop on FedKDD 2024
  • ICML-Workshop on FM-Wild 2024
  • SIGKDD-Workshop on Federated Learning for Distributed Data Mining (FL4Data) 2023
• External Reviewer
  • IEEE International Conference on Data Engineering (ICDE) 2020-2021
  • Network and Distributed System Security Symposium (NDSS) 2025

👩‍🏫 Teaching & Talks

• A Unified Weighted-Distance Framework for No-Box Membership Inference Attacks on Synthetic Gene Expression Data (ELSA Health Privacy Challenge, Red Team), Invited Speaker @CAMDA, ISMB 2026
• Quantifying and Understanding Membership Inference Risk in Genomic Language Models, @Differential Privacy for Health and Genomics Workshop (OpenDP, Harvard University), 2026
• Tutorial Co-Speaker @IEEE BigData 2025, Data Privacy in the Age of AI and LLMs: Attacks, Defenses and Emerging Challenges
• Privacy Challenge as Models Scale: Training Efficiency and Amplified Risk, @University of Virginia, AI ML seminar
• Co-instructor @Emory University, CS573 fall 2024
• Guest lecturer @Hokkaido University, Theory and Practice of Algorithms, 2023 Spring