Skip to main content
Assured Autonomy Tools Portal
Continual Assurance of Learning-Enabled, Cyber-Physical Systems (LE-CPS)

OVERT: Verification of nonlinear dynamical systems with neural network controllers via overapproximation


Neural network verification is an important tool for reasoning about the correct behavior of safety-critical deep learning-based systems. We contribute a methodology for verification of closed-loop systems with neural network controllers. Our method uses a sound overapproximation constructed with bounded dynamics models. It may be implemented with any neural network verification tool, which allows our method to trade off the benefits and drawbacks of different tools depending on the specific problem at hand.

Year of Publication
Conference Name
Workshop on Safe Machine Learning, International Conference on Learning Representations