Reference : Simulator-based explanation and debugging of hazard-triggering events in DNN-based sa...

	Document type :	Scientific journals : Article
	Discipline(s) :	Engineering, computing & technology : Computer science
	Focus Areas :	Computational Sciences
	To cite this reference:	http://hdl.handle.net/10993/52366

Title :	Simulator-based explanation and debugging of hazard-triggering events in DNN-based safety-critical systems
Language :	English
Author, co-author :	Fahmy, Hazem [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SVV >]
	Pastore, Fabrizio [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SVV >]
	Briand, Lionel [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SVV >]
	Stifter, Thomas []
Publication date :	In press
Journal title :	ACM Transactions on Software Engineering and Methodology
Publisher :	Association for Computing Machinery (ACM)
Peer reviewed :	Yes
Audience :	International
ISSN :	1049-331X
Country :	United States
Keywords :	[en] DNN Explanation ; Search-based Testing ; Functional Safety ; Debugging ; AI
Abstract :	[en] When Deep Neural Networks (DNNs) are used in safety-critical systems, engineers should determine the safety risks associated with failures (i.e., erroneous outputs) observed during testing. For DNNs processing images, engineers visually inspect all failure-inducing images to determine common characteristics among them. Such characteristics correspond to hazard-triggering events (e.g., low illumination) that are essential inputs for safety analysis. Though informative, such activity is expensive and error-prone. To support such safety analysis practices, we propose SEDE, a technique that generates readable descriptions for commonalities in failure-inducing, real-world images and improves the DNN through effective retraining. SEDE leverages the availability of simulators, which are commonly used for cyber-physical systems. It relies on genetic algorithms to drive simulators towards the generation of images that are similar to failure-inducing, real-world images in the test set; it then employs rule learning algorithms to derive expressions that capture commonalities in terms of simulator parameter values. The derived expressions are then used to generate additional images to retrain and improve the DNN. With DNNs performing in-car sensing tasks, SEDE successfully characterized hazard-triggering events leading to a DNN accuracy drop. Also, SEDE enabled retraining leading to significant improvements in DNN accuracy, up to 18 percentage points.
Research centres :	Interdisciplinary Centre for Security, Reliability and Trust (SnT) > Software Verification and Validation Lab (SVV Lab)
Funders :	European Commission - EC
Name of the research project :	BRIDGES2020/IS/14711346/FUNTASY
Target :	Researchers ; Professionals ; Students
Permalink :	http://hdl.handle.net/10993/52366
Other URL :	https://github.com/sntsvv/sede
Framework Programme / European Project :	H2020 ; 694277 - TUNE - Testing the Untestable: Model Testing of Complex Software-Intensive Systems
FnR project :	FnR ; FNR14711346 > Fabrizio Pastore > FUNTASY > Functional Safety For Autonomous Systems > 01/08/2020 > 31/07/2023 > 2020

	File(s) associated to this reference
	Fulltext file(s): File Commentary Version Size Access Open access SimulatorBasedExplanation.pdf Author postprint 1.25 MB View/Open

All documents in ORBi^lu are protected by a user license.

 

University of Luxembourg Library |  Feedback |  Legal notices Site Map