Seminar by Radoslav Ivanov

Details

Title: Safe autonomy within reach: a verified machine learning and control perspective

Abstract: In this talk, I will present my group’s work on assuring the safety of modern autonomous systems. In the first part of the talk, I will describe our approach, Verisig, for safety verification of autonomous systems with neural network components. I will present an exhaustive evaluation on a neural-network-controlled (1/10-scale) autonomous racing car, in terms of modeling, verification and experiments on the real platform. In the second part, I will discuss our recent work on using differential geometry to identify data flow paths in a trained neural network, with the goal of providing a neuro-symbolic analysis tool that can be used to understand safety vulnerabilities in neural networks, such as robustness issues.

Bio: Radoslav Ivanov is an Assistant Professor in Computer Science at the Rensselaer Polytechnic Institute. Prior to that, he was a postdoc at the PRECISE center at the University of Pennsylvania. Dr. Ivanov received the B.A. degree in computer science and economics from Colgate University in 2011, and the Ph.D. degree in computer and information science from the University of Pennsylvania in 2017. His research interests are broadly in the field of safe and secure autonomy, with a focus on verified machine learning, control theory and cyber-physical security. The natural application domains of his work are automotive and medical cyber-physical systems. Dr. Ivanov’s work has been recognized by the AFOSR Young Investigator Program Award, the Outstanding Early Research Award at RPI, as well as a best paper award at ACM TECS.

Location: MALA 7200