Concept Enforcement and Modularization for the ISO 26262 Safety Case of Neural Networks




Faculty/Professorship: Cognitive Systems  
Author(s): Schwalbe, Gesina  ; Schmid, Ute  
Corporate Body: PhD Forum at the European Conference on Machine Learning and Principles of Knowledge Discovery (ECML), 2019, Würzburg
Publisher Information: Bamberg : Otto-Friedrich-Universität
Year of publication: 2020
Pages: 6
Language(s): English
DOI: 10.20378/irb-47277
Licence: Creative Commons - CC BY-SA - Attribution - ShareAlike 4.0 International 
URL: https://ecmlpkdd2019.org/submissions/phdforum/
URN: urn:nbn:de:bvb:473-irb-472771
Abstract: 
The ability to formulate formally verifiable requirements is crucial for the safety verification of software units in the automotive industries. However, it is very restricted for complex perception tasks involving deep neural networks (DNNs) due to their black-box character. For a solution we propose to identify or enforce human interpretable concepts as intermediate output of the DNN. Two effects are expected: Requirements can be formulated using these concepts. And the DNN is modularized, thus reduces complexity and therefore easing a safety case. A research project proposal for a PhD thesis is sketched in the following.
SWD Keywords: ISO/DIS 26262 ; Neurales Netzwerk ; Verifikation
Keywords: ISO 26262, neural networks, formal verification, concept enforcement
DDC Classification: 004 Computer science  
RVK Classification: ST 300   
Document Type: Workingpaper
URI: https://fis.uni-bamberg.de/handle/uniba/47277
Release Date: 3. July 2020

File Description SizeFormat  
fisba47277.pdf889.15 kBAdobe PDFView/Open