Extending Neural Network Verification to a Larger Family of Piece-wise Linear Activation Functions

In this paper, we extend an available neural network verification technique to support a wider class of piece-wise linear activation functions. Furthermore, we extend the algorithms, which provide in their original form exact respectively over-approximative results for bounded input sets represented as start sets, to allow also unbounded input set. We implemented our algorithms and demonstrated their effectiveness in some case studies.
Comment: In Proceedings FMAS 2023, arXiv:2311.08987