Generalizing neural network verification to the family of piece-wise linear activation functions
László Antal, Erika Ábrahám, Hana Masara · Science of Computer Programming · 2025
In this paper, we extend an available neural network verification technique to support the full 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 star sets, to allow also unbounded input sets. We implemented our algorithms and demonstrate their effectiveness on some case studies.