Toward Scalable Verification for Safety-Critical Deep Networks

Simple item page
dc.contributor.authorKuper, Lindsey
dc.contributor.authorGottschlich, Justin E
dc.contributor.authorGottschlich, Justin E
dc.contributor.authorJulian, Kyle
dc.contributor.authorBarrett, Clark
dc.contributor.authorKochenderfer, Mykel J
dc.date2023-05-18T00:14:45.000
dc.date.accessioned2023-05-22T13:06:45Z
dc.date.available2023-05-22T13:06:45Z
dc.date.issued2018-01-01
dc.date.submitted2020-12-18T14:10:05-08:00
dc.description.abstractThe increasing use of deep neural networks for safety-critical applications, such as autonomous driving and flight control, raises concerns about their safety and reliability. Formal verification can address these concerns by guaranteeing that a deep learning system operates as intended, but the state of the art is limited to small systems. In this work-in-progress report we give an overview of our work on mitigating this difficulty, by pursuing two complementary directions: devising scalable verification techniques, and identifying design choices that result in deep learning systems that are more amenable to verification.
dc.identifier.urihttps://repository.upenn.edu/handle/20.500.14332/8486
dc.legacy.articleid1010
dc.legacy.fulltexturlhttps://repository.upenn.edu/cgi/viewcontent.cgi?article=1010&context=cps_machine_programming&unstamped=1
dc.source.issue11
dc.source.journalMachine Programming
dc.source.statuspublished
dc.titleToward Scalable Verification for Safety-Critical Deep Networks
dc.typePresentation
digcom.contributor.authorKuper, Lindsey
digcom.contributor.authorKatz, Guy
digcom.contributor.authorisAuthorOfPublication|email:gojustin@cis.upenn.edu|institution:Intel|Gottschlich, Justin E
digcom.contributor.authorJulian, Kyle
digcom.contributor.authorBarrett, Clark
digcom.contributor.authorKochenderfer, Mykel J
digcom.identifiercps_machine_programming/11
digcom.identifier.contextkey20689406
digcom.identifier.submissionpathcps_machine_programming/11
digcom.typeconference
dspace.entity.typePublication
relation.isAuthorOfPublication5cbcf403-a558-4c1c-aa8a-d700e3d50679
relation.isAuthorOfPublication5cbcf403-a558-4c1c-aa8a-d700e3d50679
relation.isAuthorOfPublication.latestForDiscovery5cbcf403-a558-4c1c-aa8a-d700e3d50679
upenn.schoolDepartmentCenterMachine Programming
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
1801.05950.pdf
Size:
711.09 KB
Format:
Adobe Portable Document Format
Download
Collection
Presentations