DeepCDCL: An CDCL-based Neural Network Verification Framework
This addresses verification challenges for neural networks in safety-critical domains, though it appears incremental as an adaptation of existing CDCL methods.
The authors tackled the problem of verifying neural networks in safety-critical applications by proposing DeepCDCL, a verification framework based on the Conflict-Driven Clause Learning algorithm, which achieved significant speed-ups on ACAS Xu and MNIST datasets.
Neural networks in safety-critical applications face increasing safety and security concerns due to their susceptibility to little disturbance. In this paper, we propose DeepCDCL, a novel neural network verification framework based on the Conflict-Driven Clause Learning (CDCL) algorithm. We introduce an asynchronous clause learning and management structure, reducing redundant time consumption compared to the direct application of the CDCL framework. Furthermore, we also provide a detailed evaluation of the performance of our approach on the ACAS Xu and MNIST datasets, showing that a significant speed-up is achieved in most cases.