Departmental Papers (CIS)

Date of this Version

12-2020

Document Type

Journal Article

Abstract

This paper 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.

Subject Area

CPS Formal Methods, CPS Safe Autonomy

Publication Source

ACM Transactions on Embedded Computing Systems (TECS)

Volume

1

Issue

1

Start Page

1

Last Page

26

Keywords

software and its engineering, formal methods, computer systems organization, embedded and cyber-physical systems, computing methodologies, neural networks

Share

COinS
 

Date Posted:04 January 2021

This document has been peer reviewed.