Verifying the Safety of Autonomous Systems with Neural Network Controllers
Abstract
This article addresses the problem of verifying the safety of autonomous systems with neural network (NN) controllers. We focus on NNs with sigmoid/tanh activations and use the fact that the sigmoid/tanh is the solution to a quadratic differential equation. This allows us to convert the NN into an equivalent hybrid system and cast the problem as a hybrid system verification problem, which can be solved by existing tools. Furthermore, we improve the scalability of the proposed method by approximating the sigmoid with a Taylor series with worst-case error bounds. Finally, we provide an evaluation over four benchmarks, including comparisons with alternative approaches based on mixed integer linear programming as well as on star sets.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Dec 07, 2020
- Source ID
- 10.1145/3419742
Entities
People
- George J. Pappas
- Insup Lee
- James Weimer
- Radoslav Ivanov
- Rajeev Alur
- Taylor J. Carpenter
Organizations
- Air Force Research Laboratory
- University of Pennsylvania