DeepHyperion: Exploring the Feature Space of Deep Learning-Based Systems through Illumination Search
Thu 15 Jul 2021 10:10 - 10:30 at ISSTA 1 - Session 9 (time band 3) Testing Deep Learning Systems 3 Chair(s): Mauro Pezze
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.
Wed 14 JulDisplayed time zone: Brussels, Copenhagen, Madrid, Paris change
19:40 - 20:20
|DeepHyperion: Exploring the Feature Space of Deep Learning-Based Systems through Illumination Search|
Tahereh Zohdinasab USI Lugano, Vincenzo Riccio USI Lugano, Alessio Gambi University of Passau, Paolo Tonella USI LuganoDOI File Attached
|Automatic Test Suite Generation for Key-Points Detection DNNs using Many-Objective Search (Experience Paper)|
Fitash Ul Haq University of Luxembourg, Donghwan Shin University of Luxembourg, Lionel Briand University of Luxembourg; University of Ottawa, Thomas Stifter IEE, Jun Wang Post LuxembourgDOI