Seminars on security and privacy in machine learning: Bo Li (University of Illinois Urbana-Champaign)

Date
Jun 14, 2022, 1:00 pm2:30 pm
Location
Virtual
Speaker
Event Description

Abstract: TBD

Bio: 

I am an Assistant Professor in the Computer Science Department at University of Illinois at Urbana-Champaign. My research focuses on machine learning, security, privacy, and game theory. Specifically, much of our work aims at exploring vulnerabilities of machine learning systems to various adversarial attacks, and endeavors to develop real-world robust learning systems.

The long-term goal for our group, Secure learning lab (SL2), is to make machine learning algorithms more robust, private, efficient, and interpretable. We have worked on exploring different types of adversarial attacks including evasion and poisoning attacks in digital and physical worlds with different constraints. We have developed and will continue to explore robust learning algorithms based on game theory, prior knowledge of data distribution, as well as properties of learning tasks. Our work directly benefits applications such as computer vision, natural language process, audio recognition, and privacy preserving machine learning systems.