Abstract

In this talk I will focus on the interaction with the model-checking tool: writing specifications and understanding the model checker’s output. I will argue that tools like learning and causality can help with both tasks and reduce the amount of human effort required for verification. I will further discuss how explanations can help us to understand the model. I will briefly touch on the theory of actual causality and illustrate the definitions by examples from formal verification. I will also argue that active learning can be viewed as a type of causal discovery.  Bio: Hana Chockler is a Principal Scientist at a startup company causaLens and a Reader (Associate Professor) in Formal Methods in the Department of Informatics at King’s College London (KCL). Prior to joining KCL in 2013, Hana worked at IBM Research in the formal verification and software engineering departments. Her research interests span a wide variety of topics, including formal verification and synthesis of hardware and software, fundamental concepts in causality and its applications to a variety of domains, learning, and explainable AI.