[CPS-IoT Week Workshop] Provably Safe Perception in Cyber-Physical Systems

Deep Samal, Dung Tran, and Marilyn Wolf are organizing a new workshop at CPS-IoT Week this year: the International Workshop on Perception for Safety-Critical Cyber-Physical Systems (PerCPS ’23).  This workshop is intended to provide a bridge between machine learning for perception and cyber-physical systems. Perception is a critical capability for autonomous cyber-physical systems.  Cyber-physical automatons need to be able to…

[ICCPS’22] Best Paper: interpretable Detection of Distribution Shifts in Learning Enabled Cyber-Physical Systems

Introduction Autonomous systems with learning-enabled components (LECs) rely on deep neural networks in order to achieve high performance for various applications. It is well known that neural networks are vulnerable to distribution shifts (e.g., weather changes and adversarial perturbations). This vulnerability raises the safety and robustness concerns of learning-enabled cyber-physical systems (CPS) in the real world. For instance, in an…