KOPS - The Institutional Repository of the University of Konstanz

SpecRepair : Counter-Example Guided Safety Repair of Deep Neural Networks

SpecRepair : Counter-Example Guided Safety Repair of Deep Neural Networks

Cite This

Files in this item

Checksum: MD5:6651827aac6bc98002a7d2f1e10793ab

BAUER-MARQUART, Fabian, David BOETIUS, Stefan LEUE, Christian SCHILLING, 2022. SpecRepair : Counter-Example Guided Safety Repair of Deep Neural Networks. Model Checking Software : 28th International Symposium, SPIN 2022 (virtual), May 21, 2022. In: LEGUNSEN, Owolabi, ed., Grigore ROSU, ed.. Model Checking Software : 28th International Symposium, SPIN 2022, Virtual Event, May 21, 2022 : Proceedings. Cham:Springer, pp. 79-96. ISSN 0302-9743. eISSN 1611-3349. ISBN 978-3-031-15076-0. Available under: doi: 10.1007/978-3-031-15077-7_5

@inproceedings{BauerMarquart2022SpecR-59172, title={SpecRepair : Counter-Example Guided Safety Repair of Deep Neural Networks}, year={2022}, doi={10.1007/978-3-031-15077-7_5}, number={13255}, isbn={978-3-031-15076-0}, issn={0302-9743}, address={Cham}, publisher={Springer}, series={Lecture Notes in Computer Science}, booktitle={Model Checking Software : 28th International Symposium, SPIN 2022, Virtual Event, May 21, 2022 : Proceedings}, pages={79--96}, editor={Legunsen, Owolabi and Rosu, Grigore}, author={Bauer-Marquart, Fabian and Boetius, David and Leue, Stefan and Schilling, Christian} }

<rdf:RDF xmlns:dcterms="http://purl.org/dc/terms/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:bibo="http://purl.org/ontology/bibo/" xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:void="http://rdfs.org/ns/void#" xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > <rdf:Description rdf:about="https://kops.uni-konstanz.de/rdf/resource/123456789/59172"> <foaf:homepage rdf:resource="http://localhost:8080/jspui"/> <dc:creator>Schilling, Christian</dc:creator> <dc:contributor>Leue, Stefan</dc:contributor> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/59172"/> <dc:creator>Leue, Stefan</dc:creator> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/rdf/resource/123456789/36"/> <dcterms:issued>2022</dcterms:issued> <dc:contributor>Schilling, Christian</dc:contributor> <dc:creator>Bauer-Marquart, Fabian</dc:creator> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-11-16T12:02:29Z</dcterms:available> <dcterms:title>SpecRepair : Counter-Example Guided Safety Repair of Deep Neural Networks</dcterms:title> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dc:rights>terms-of-use</dc:rights> <dc:language>eng</dc:language> <dc:contributor>Boetius, David</dc:contributor> <dcterms:abstract xml:lang="eng">Deep neural networks (DNNs) are increasingly applied in safety-critical domains, such as self-driving cars, unmanned aircraft, and medical diagnosis. It is of fundamental importance to certify the safety of these DNNs, i.e. that they comply with a formal safety specification. While safety certification tools exactly answer this question, they are of no help in debugging unsafe DNNs, requiring the developer to iteratively verify and modify the DNN until safety is eventually achieved. Hence, a repair technique needs to be developed that can produce a safe DNN automatically. To address this need, we present SpecRepair, a tool that efficiently eliminates counter-examples from a DNN and produces a provably safe DNN without harming its classification accuracy. SpecRepair combines specification-based counter-example search and resumes training of the DNN, penalizing counter-examples and certifying the resulting DNN. We evaluate SpecRepair’s effectiveness on the ACAS Xu benchmark, a DNN-based controller for unmanned aircraft, and two image classification benchmarks. The results show that SpecRepair is more successful in producing safe DNNs than comparable methods, has a shorter runtime, and produces safe DNNs while preserving their classification accuracy.</dcterms:abstract> <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-11-16T12:02:29Z</dc:date> <dc:contributor>Bauer-Marquart, Fabian</dc:contributor> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/rdf/resource/123456789/36"/> <dc:creator>Boetius, David</dc:creator> </rdf:Description> </rdf:RDF>

This item appears in the following Collection(s)

Search KOPS


Browse

My Account