Concolic Testing for Deep Neural Networks

Authors:

Preprint

4 August 2018

preprint
Published by arXiv in arXiv

DOI:10.48550/arXiv.1805.00089

Abstract

Concolic testing combines program execution and symbolic analysis to explore the execution paths of a software program. This paper presents the first concolic testing approach for Deep Neural Networks (DNNs). More specifically, we formalise coverage criteria for DNNs that have been studied in the literature, and then develop a coherent method for performing concolic testing to increase test coverage. Our experimental results show the effectiveness of the concolic testing approach in both achieving high coverage and finding adversarial examples.

Keywords

All Related Versions

This publication has 4 references indexed in Scilit:

A game-based approximate verification of deep neural networks with provable guarantees
Theoretical Computer Science, 2020
A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction
IEEE Transactions on Information Theory, 2017
CUTE: A Concolic Unit Testing Engine for C
2005
Test input generation with java PathFinder
ACM SIGSOFT Software Engineering Notes, 2004