SAVER: A Toolbox for Sampling-Based, Probabilistic Verification of Neural Networks
This provides a probabilistic verification tool for neural networks, which is incremental as it builds on sampling-based methods and set containment definitions.
The paper tackles the problem of verifying neural networks by assessing the probability that their outputs satisfy constraints for given input distributions, and it synthesizes set expansions to achieve desired satisfaction probabilities with user-specified confidence levels.
We present a neural network verification toolbox to 1) assess the probability of satisfaction of a constraint, and 2) synthesize a set expansion factor to achieve the probability of satisfaction. Specifically, the tool box establishes with a user-specified level of confidence whether the output of the neural network for a given input distribution is likely to be contained within a given set. Should the tool determine that the given set cannot satisfy the likelihood constraint, the tool also implements an approach outlined in this paper to alter the constraint set to ensure that the user-defined satisfaction probability is achieved. The toolbox is comprised of sampling-based approaches which exploit the properties of signed distance function to define set containment.