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

Tags

Fields of Study

  • Computer science

Readers

  • Calculus or Mathematical Analysis
  • Computer Science/Computer Engineering/Data Science/Digital Signal Processing.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks
  • Autonomy
  • Autonomy - Autonomous System Control