Report Open Access

DeepMetis: Augmenting a Deep Learning Test Set to Increase its Mutation Score

Vincenzo Riccio; Nargiz Humbatova; Gunel Jahangirova; Paolo Tonella

Deep Learning (DL) components are routinely integrated into software systems that need to perform complex tasks such as image or natural language processing. The adequacy of the test data used to test such systems can be assessed by their ability to expose artificially injected faults (mutations) that simulate real DL faults.

In this paper, we describe an approach to automatically generate new test inputs that can be used to augment the existing test set so that its capability to detect DL mutations increases. Our tool DeepMetis implements a search based input generation strategy. To account for the non-determinism of the training and the mutation processes, our fitness function involves multiple instances of the DL model under test. Experimental results show that DeepMetis is effective at augmenting the given test set, increasing its capability to detect mutants by 63% on average. A leave-one-out experiment shows that the augmented test set is capable of exposing unseen mutants, which simulate the occurrence of yet undetected faults.

Files (960.8 kB)
Name Size
960.8 kB Download
All versions This version
Views 4848
Downloads 2121
Data volume 20.2 MB20.2 MB
Unique views 4747
Unique downloads 2020


Cite as