The VeriNet toolkit for verification of neural networks
The VeriNet toolkit is a state-of-the-art sound and complete symbolic interval propagation based toolkit for verification of neural networks. VeriNet won second place overall and was the most performing among toolkits not using GPUs in the 2nd international verification of neural networks competition. VeriNet is devloped at the Verification of Autonomous Systems (VAS) group, Imperial College London.
Relevant Publications.
VeriNet is developed as part of the following publications:
Efficient Neural Network Verification via Adaptive Refinement and Adversarial Search
This version of VeriNet subsumes the VeriNet toolkit publised in the first paper and the DeepSplit toolkit published in the second paper.