Adaptive Metamorphic Testing with Contextual Bandits

TL;DR

This paper introduces Adaptive Metamorphic Testing, which employs contextual bandits to dynamically select metamorphic relations, improving fault detection in machine learning systems like image classification and object detection.

Contribution

It presents a novel approach combining metamorphic testing with reinforcement learning to adaptively select relations, enhancing testing effectiveness for systems with uncertain or missing expected outputs.

Findings

Effectively identifies system weaknesses and robustness boundaries.

Learns which metamorphic relations are most likely to discover faults.

Improves fault detection efficiency in machine learning applications.

Abstract

Metamorphic Testing is a software testing paradigm which aims at using necessary properties of a system-under-test, called metamorphic relations, to either check its expected outputs, or to generate new test cases. Metamorphic Testing has been successful to test programs for which a full oracle is not available or to test programs for which there are uncertainties on expected outputs such as learning systems. In this article, we propose Adaptive Metamorphic Testing as a generalization of a simple yet powerful reinforcement learning technique, namely contextual bandits, to select one of the multiple metamorphic relations available for a program. By using contextual bandits, Adaptive Metamorphic Testing learns which metamorphic relations are likely to transform a source test case, such that it has higher chance to discover faults. We present experimental results over two major case studies in machine learning, namely image classification and object detection, and identify weaknesses and robustness boundaries. Adaptive Metamorphic Testing efficiently identifies weaknesses of the tested systems in context of the source test case.