Research Statement

• Machine learning has recently been widely adopted in various applications, and such success is largely due to a combination of algorithmic breakthroughs, computation resource improvements, and especially the access to a large amount of diverse training data. However, such massive data usually contain privacy sensitive information such as medical and financial information of individuals. With the rise of ubiquitous sensing, personalization, and virtual assistants, users' privacy is at ever-increasing risk. Can we enable the power and utility of machine learning and data analytics while still ensuring users' privacy? Can we design privacy-preserving learning algorithms that can ensure privacy and guarantee high data utility? Can we design privacy-preserving data generative models for general downstream tasks?

  Here we aim to explore novel techniques including differential privacy, homomorphic encryption, and information theoretic analysis to enable privacy-preserving machine learning and data analytics in practice. Our long-term goal is to both provide practical real-world solutions to privacy-preserving machine learning and data analytics and deepen the theoretical understanding of data privacy in the big data era.

Recent Publications

• Unified privacy attacks

• Privacy-preserving data generation

Unified privacy attacks

SecretGen: Privacy Recovery on Pre-trained Models via Distribution Discrimination Zhuowen Yuan, Fan Wu, Yunhui Long, Chaowei Xiao, Bo Li. ECCV 2022

LinkTeller: Recovering Private Edges from Graph Neural Networks via Influence Analysis Fan Wu, Yunhui Long, Ce Zhang, Bo Li. IEEE Symposium on Security and Privacy (Oakland), 2022

Characterizing Attacks on Deep Reinforcement Learning Xinlei Pan, Chaowei Xiao, Warren He, Jian Peng, Mingjie Sun, Jinfeng Yi, Bo Li, Dawn Song. AAMAS 2022 (Oral Presentation)

Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks Yuheng Zhang, Ruoxi Jia, Hengzhi Pei, Wenxiao Wang, Bo Li, Dawn Song. CVPR 2020 (Oral Presentation)

How You Act Tells a Lot: Privacy-Leakage Attack on Deep Reinforcement Learning ​Xinlei Pan, Weiyao Wang, Xiaoshuai Zhang, Bo Li, Jinfeng Yi, Dawn Song. International Conference on Autonomous Agents and Multiagent Systems (AAMAS). May, 2019

Privacy-preserving data generation

G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminators Yunhui Long*, Boxin Wang*, Zhuolin Yang, Bhavya Kailkhura, Aston Zhang, Carl A. Gunter, Bo Li. NeurIPS 2021

DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation Boxin Wang*, Fan Wu*, Yunhui Long*, Luka Rimanic, Ce Zhang, Bo Li. CCS 2021

Application-Driven Privacy-Preserving Data Publishing with Correlated Attributes Aria Rezaei, Chaowei Xiao, Jie Gao, Bo Li, Sirajum Munir. Embedded Wireless Systems and Networks (EWSN 2021) (Best Paper Award)

Iterative classification for sanitizing large-scale datasets ​B. Li, Y. Vorobeychik, M. Li, and B. Malin. ICDM 2015