Continuous Safety Verification of Neural Networks
This addresses the challenge of continuous safety verification for neural networks in autonomous driving, which is incremental as it builds on existing verification methods.
The paper tackles the problem of maintaining safety verification for neural networks in autonomous driving as they evolve, by developing conditions that allow reusing previous verification results to analyze only a small part of the modified network, evaluated on a scaled vehicle with a DNN controller.
Deploying deep neural networks (DNNs) as core functions in autonomous driving creates unique verification and validation challenges. In particular, the continuous engineering paradigm of gradually perfecting a DNN-based perception can make the previously established result of safety verification no longer valid. This can occur either due to the newly encountered examples (i.e., input domain enlargement) inside the Operational Design Domain or due to the subsequent parameter fine-tuning activities of a DNN. This paper considers approaches to transfer results established in the previous DNN safety verification problem to the modified problem setting. By considering the reuse of state abstractions, network abstractions, and Lipschitz constants, we develop several sufficient conditions that only require formally analyzing a small part of the DNN in the new problem. The overall concept is evaluated in a $1/10$-scaled vehicle that equips a DNN controller to determine the visual waypoint from the perceived image.