DeepCDCL: An CDCL-based Neural Network Verification Framework

arXiv:2403.07956v1 Announce Type: new
Abstract: 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 …

abstract algorithm applications arxiv asynchronous concerns conflict cs.ai cs.lg face framework management network networks neural network neural networks novel paper safety safety-critical security security concerns type verification