A new proof format (APTP) and an efficient proof checker (APTPchecker) make neural network verification more reliable and robust across different tools.

We propose an assume-guarantee compositional framework, CoVeNN, to scale verification to large networks. CoVeNN can verify nearly 7 times more problems than state-of-the-art verifiers.

Generative AI is inherently unreliable and not appropriate in environments that could result in the loss of life until hallucinations are addressed.