Bo Li
Recent News:
I will join the CS department at University of Illinois at Urbana–Champaign as an Assistant Professor in June 2018, and I am looking for Ph.D. students!
I am currently a Postdoctoral Fellow at the EECS department at UC Berkeley University, working with Prof. Dawn Song.
My research focuses on both theoretical and practical aspects of machine learning, security, privacy, game theory, social networks, and adversarial deep learning.
For students at UIUC: If you are interested in working with me, please email me directly.
For prospective students who are planning to apply for Ph.D. programs: If you are interested in working with me, please apply for the Ph.D. Program in UIUC/CS and mention your interest in my work to ensure that I see your application.
About
I am a recipient of the Symantec Research Labs Graduate Fellowship. I have designed several robust learning algorithms, a scalable framework for achieving robustness for a range of learning methods, and a privacy preserving data publishing system. I am currently working on anomaly detection systems against causative poisoning attacks and malware detection with real world collected big data. I'm also working on adversarial deep learning for training generative adversarial networks (GAN) and designing robust deep neural networks against adversarial examples. I utilize game theoretic analyses to model the interactions between an intelligent adversary and a machine learning system as, allowing us to design robust learning strategies that explicitly account for an adversary’s optimal response. Another focus of my current research is to develop scalable robust algorithms that can process massive amounts of data available for Internet-scale problems regarding specific cloud computing infrastructure to achieve large-scale secure learning for big data.
Previously I have worked on Information security, Network security, MRI analysis, and other Healthcare related research, and I'm still interested in these topics. If you have any common interests, feel free to contact me and let's have a discussion.