Adaptive Metamorphic Testing with Contextual Bandits
This work addresses the challenge of testing machine learning systems where full oracles are unavailable, offering an adaptive method to improve fault detection, though it is incremental as it builds on existing metamorphic testing with a reinforcement learning technique.
The paper tackles the problem of selecting effective metamorphic relations for testing machine learning systems by proposing Adaptive Metamorphic Testing, which uses contextual bandits to learn and choose relations that are more likely to discover faults, resulting in efficient identification of weaknesses in image classification and object detection systems.
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.