Fully Automatic Neural Network Reduction for Formal Verification

arXiv:2305.01932v2 Announce Type: replace
Abstract: Formal verification of neural networks is essential before their deployment in safety-critical applications. However, existing methods for formally verifying neural networks are not yet scalable enough to handle practical problems involving a large number of neurons. We address this challenge by introducing a fully automatic and sound reduction of neural networks using reachability analysis. The soundness ensures that the verification of the reduced network entails the verification of the original network. To the best of …

abstract applications arxiv challenge cs.lg deployment however network networks neural network neural networks neurons practical safety safety-critical scalable sound type verification