Report Open Access

DeepHyperion: Exploring the Feature Space of Deep Learning-Based Systems through Illumination Search

Tahereh Zohdinasab; Vincenzo Riccio; Alessio Gambi; Paolo Tonella

Deep Learning (DL) has been successfully applied to a wide range of application domains, including safety-critical ones. Several DL testing approaches have been recently proposed in the literature but none of them aims to assess how different interpretable features of the generated inputs affect the system's behaviour.

In this paper, we resort to Illumination Search to find the highest-performing test cases (i.e., misbehaving and closest to misbehaving), spread across the cells of a map representing the feature space of the system. We introduce a methodology that guides the users of our approach in the tasks of identifying and quantifying the dimensions of the feature space for a given domain. We developed DeepHyperion, a search-based tool for DL systems that illuminates, i.e., explores at large, the feature space, by providing developers with an interpretable feature map where automatically generated inputs are placed along with information about the exposed behaviours.

Files (3.8 MB)
Name Size
TR-Precrime-2021-05.pdf
md5:3f4afea860c8e52eee8aaf8b35f8cb5d
3.8 MB Download
31
31
views
downloads
All versions This version
Views 3131
Downloads 3131
Data volume 119.1 MB119.1 MB
Unique views 2929
Unique downloads 3030

Share

Cite as