Compositional Inductive Invariant Based Verification of Neural Network Controlled Systems

arXiv:2312.10842v2 Announce Type: replace-cross
Abstract: The integration of neural networks into safety-critical systems has shown great potential in recent years. However, the challenge of effectively verifying the safety of Neural Network Controlled Systems (NNCS) persists. This paper introduces a novel approach to NNCS safety verification, leveraging the inductive invariant method. Verifying the inductiveness of a candidate inductive invariant in the context of NNCS is hard because of the scale and nonlinearity of neural networks. Our compositional method makes this verification …

abstract arxiv challenge cs.lg cs.lo cs.sy eess.sy however inductive integration network networks neural network neural networks novel paper safety safety-critical systems type verification