Verification of Neural Networks for Safety and Security-critical Domains

In recent times, machine learning has gained incredible traction in the artificial intelligence community, and neural networks in particular have been leveraged in many successful applications originating from various domains. However, it is hard to provide any formal guarantee on the behavior of this kind of models, and therefore their reliability is still in doubt, especially concerning their deployment in safety and security-critical applications. In this work, we will present our contributions on the topic of formal verification, which recently emerged as a promising solution to address some of these problems. We will also present two novel use cases originating from real-world applications we are working on and the related challenges and perspectives.