DLS - Patrick McDaniel, "Adversarial Machine Learning: A 10-year Perspective"

Abstract:
Machine learning is revolutionizing technology and society. However, like any technology, it can be misused by adversaries and our understanding of the potential threats remains limited. If machine learning is to part of any critical decision making process, we must be able to detect and mitigate threats at both training and inference phases. Over the past decade, I have studied a myriad of threats to machine learning at all stages of its lifecycle and proposed a variety of methods that bring us closer towards trustworthy machine learning systems. In this talk, I will discuss the arc of adversarial machine learning, how threat models have evolved, and how the community has gained new insights into the root causes of the vulnerabilities present in machine learning systems today.

Bio: 
Patrick McDaniel is the Tsun-Ming Shih Professor of Computer Sciences in the School of Computer, Data & Information Sciences at the University of Wisconsin-Madison. Professor McDaniel is a Fellow of IEEE, ACM and AAAS, a recipient of the SIGOPS Hall of Fame Award and SIGSAC Outstanding Innovation Award, and the director of the NSF Frontier Center for Trustworthy Machine Learning. He also served as the program manager and lead scientist for the Army Research Laboratory's Cyber-Security Collaborative Research Alliance from 2013 to 2018. Patrick's research focuses on a wide range of topics in computer and network security and technical public policy. Prior to joining Wisconsin in 2022, he was the William L. Weiss Professor of Information and Communications Technology and Director of the Institute for Networking and Security Research at Pennsylvania State University. 
 
Research Interests: Dr. McDaniel's research focuses on a wide range of topics in computer and network security and technical public policy, with interests in mobile device security, the security of machine learning, systems, program analysis for security, sustainability and election systems.