Robustness Verifcation in Neural Networks

arXiv:2403.13441v1 Announce Type: cross
Abstract: In this paper we investigate formal verification problems for Neural Network computations. Of central importance will be various robustness and minimization problems such as: Given symbolic specifications of allowed inputs and outputs in form of Linear Programming instances, one question is whether there do exist valid inputs such that the network computes a valid output? And does this property hold for all valid inputs? Do two given networks compute the same function? Is there a …

abstract arxiv cs.ai cs.lg form importance inputs instances linear network networks neural network neural networks paper programming question robustness type verification will