ECE Research Seminar by Ren Wang

Please join the Department of Electrical and Computer Engineering in the Siegel Hall Auditorium at 12:45 p.m. (CST) on Friday, November 11, for another ECE Research Seminar. Ren Wang, the newest faculty member in the ECE department, will be the guest speaker. Wang will speak on his research, “Practical Attacks and Defenses in Machine Learning Systems,”

Light refreshments will be provided.

Abstract

Despite the fact that machine learning systems have been used for a wide range of applications, the lack of robustness has resulted in ever-growing concern over how people can trust these models in applications that require high security. In this talk, Ren Wang will start by providing a comprehensive overview of robustness assessment in the lifecycle of machine learning systems. The robustness assessment methods include training-phase backdoor poisoning attacks (a.k.a. trojan attacks) that embed backdoor patterns to a well-trained model for gaining the ability to manipulate machine decision-making and inference-phase adversarial attacks that fail machine learning systems’ decisions only by manipulating test data. Then, Wang will delve into recent practical defenses in different learning phases. The defenses cover methods to protect training data, enhance models’ intrinsic robustness, and detect and repair back-doored models. The talk will also highlight the connections between the introduced attacks and defenses with power systems, signal processing, and optimization.

Biography

Ren Wang joined the Department of Electrical and Computer Engineering at Illinois Tech as an assistant professor in 2022. Before joining Illinois Tech, he was a postdoctoral research fellow and a lecturer in the Department of Electrical Engineering and Computer Science at the University of Michigan. He received his Ph.D. from the Department of Electrical, Computer, and Systems Engineering at Rensselaer Polytechnic Institute. He received both his bachelor's degree and master's degree in electrical engineering in 2013 and 2016, respectively, from Tsinghua University. His research interests include trustworthy machine learning, high-dimensional data analysis, bio-inspired machine learning, and smart grids.