Learning Minimal NAP Specifications for Neural Network Verification

arXiv:2404.04662v1 Announce Type: new
Abstract: Specifications play a crucial role in neural network verification. They define the precise input regions we aim to verify, typically represented as L-infinity norm balls. While recent research suggests using neural activation patterns (NAPs) as specifications for verifying unseen test set data, it focuses on computing the most refined NAPs, often limited to very small regions in the input space. In this paper, we study the following problem: Given a neural network, find a minimal …

abstract aim arxiv computing cs.lg cs.pl data network neural network norm patterns research role set test type verification verify