# Discovering Boundary Values of Feature-based Machine Learning Classifiers through Exploratory Datamorphic Testing

arXiv: https://arxiv.org/abs/2110.00330 · HTML: https://mlsanity.com/paper/2110.00330/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 92 references that are in the map.
- First posted on arXiv 1 Oct 2021.

## Builds on (most cited first, 6 of 6)

- [DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars](https://mlsanity.com/paper/1708.08559/) (2017)
- [Metamorphic Testing: A New Approach for Generating Next Test Cases](https://mlsanity.com/paper/2002.12543/) (2020)
- [Morphy: A Datamorphic Software Test Automation Tool](https://mlsanity.com/paper/1912.09881/) (2019)
- [A Survey on Adaptive Random Testing](https://mlsanity.com/paper/2007.03885/) (2020)
- [Tapir: Automation Support of Exploratory Testing Using Model Reconstruction of the System Under Test](https://mlsanity.com/paper/1802.07983/) (2018)
- [Datamorphic Testing: A Methodology for Testing AI Applications](https://mlsanity.com/paper/1912.04900/) (2019)

## Built on by (most cited first, 1 of 1)

- [Operational Robustness of LLMs on Code Generation](https://mlsanity.com/paper/2602.18800/) (2026)

## Abstract (arXiv)

Testing has been widely recognised as difficult for AI applications. This paper proposes a set of testing strategies for testing machine learning applications in the framework of the datamorphism testing methodology. In these strategies, testing aims at exploring the data space of a classification or clustering application to discover the boundaries between classes that the machine learning application defines. This enables the tester to understand precisely the behaviour and function of the software under test. In the paper, three variants of exploratory strategies are presented with the algorithms implemented in the automated datamorphic testing tool Morphy. The correctness of these algorithms are formally proved. Their capability and cost of discovering borders between classes are evaluated via a set of controlled experiments with manually designed subjects and a set of case studies with real machine learning models.