Verification for Machine Learning, Autonomy, and Neural Networks Survey
It provides a comprehensive overview for researchers and practitioners in formal methods and AI, but is incremental as it synthesizes existing work without new results.
This survey reviews verification techniques for safety-critical autonomous systems, particularly focusing on learning-enabled components like deep neural networks, to address safety concerns in cyber-physical systems.
This survey presents an overview of verification techniques for autonomous systems, with a focus on safety-critical autonomous cyber-physical systems (CPS) and subcomponents thereof. Autonomy in CPS is enabling by recent advances in artificial intelligence (AI) and machine learning (ML) through approaches such as deep neural networks (DNNs), embedded in so-called learning enabled components (LECs) that accomplish tasks from classification to control. Recently, the formal methods and formal verification community has developed methods to characterize behaviors in these LECs with eventual goals of formally verifying specifications for LECs, and this article presents a survey of many of these recent approaches.