SpecRepair: Counter-Example Guided Safety Repair of Deep Neural Networks

TL;DR

SpecRepair is an automated tool that repairs unsafe deep neural networks by removing counter-examples, ensuring safety compliance without sacrificing accuracy, and demonstrating superior performance on benchmarks.

Contribution

It introduces SpecRepair, a novel method combining counter-example search and retraining to automatically produce safe DNNs with preserved accuracy.

Findings

More successful in producing safe DNNs than comparable methods

Shorter runtime for safety repair

Preserves classification accuracy while ensuring safety

Abstract

Deep neural networks (DNNs) are increasingly applied in safety-critical domains, such as self-driving cars, unmanned aircraft, and medical diagnosis. It is of fundamental importance to certify the safety of these DNNs, i.e. that they comply with a formal safety specification. While safety certification tools exactly answer this question, they are of no help in debugging unsafe DNNs, requiring the developer to iteratively verify and modify the DNN until safety is eventually achieved. Hence, a repair technique needs to be developed that can produce a safe DNN automatically. To address this need, we present SpecRepair, a tool that efficiently eliminates counter-examples from a DNN and produces a provably safe DNN without harming its classification accuracy. SpecRepair combines specification-based counter-example search and resumes training of the DNN, penalizing counter-examples and certifying the resulting DNN. We evaluate SpecRepair's effectiveness on the ACAS Xu benchmark, a DNN-based controller for unmanned aircraft, and two image classification benchmarks. The results show that SpecRepair is more successful in producing safe DNNs than comparable methods, has a shorter runtime, and produces safe DNNs while preserving their classification accuracy.