Testing Deep Learning Models: A First Comparative Study of Multiple Testing Techniques

TL;DR

This paper reviews various software testing techniques for deep learning models in vision-based systems and presents the first comparative experimental study on a classical benchmark.

Contribution

It provides an overview of multiple testing methods and offers the first experimental comparison on a standard benchmark in the field.

Findings

Differential testing reveals specific fault detection capabilities.

Metamorphic testing enhances robustness against certain perturbations.

Adversarial perturbation testing exposes vulnerabilities in DL models.

Abstract

Deep Learning (DL) has revolutionized the capabilities of vision-based systems (VBS) in critical applications such as autonomous driving, robotic surgery, critical infrastructure surveillance, air and maritime traffic control, etc. By analyzing images, voice, videos, or any type of complex signals, DL has considerably increased the situation awareness of these systems. At the same time, while relying more and more on trained DL models, the reliability and robustness of VBS have been challenged and it has become crucial to test thoroughly these models to assess their capabilities and potential errors. To discover faults in DL models, existing software testing methods have been adapted and refined accordingly. In this article, we provide an overview of these software testing methods, namely differential, metamorphic, mutation, and combinatorial testing, as well as adversarial perturbation testing and review some challenges in their deployment for boosting perception systems used in VBS. We also provide a first experimental comparative study on a classical benchmark used in VBS and discuss its results.