Show simple item record

dc.contributor.authorHamdi, Abdullah
dc.contributor.authorMüller, Matthias
dc.contributor.authorGhanem, Bernard
dc.date.accessioned2020-08-12T06:50:10Z
dc.date.available2020-08-12T06:50:10Z
dc.date.issued2020-04-03
dc.identifier.citationHamdi, A., Mueller, M., & Ghanem, B. (2020). SADA: Semantic Adversarial Diagnostic Attacks for Autonomous Applications. Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), 10901–10908. doi:10.1609/aaai.v34i07.6722
dc.identifier.issn2374-3468
dc.identifier.issn2159-5399
dc.identifier.doi10.1609/aaai.v34i07.6722
dc.identifier.urihttp://hdl.handle.net/10754/664563
dc.description.abstractOne major factor impeding more widespread adoption of deep neural networks (DNNs) is their lack of robustness, which is essential for safety-critical applications such as autonomous driving. This has motivated much recent work on adversarial attacks for DNNs, which mostly focus on pixel-level perturbations void of semantic meaning. In contrast, we present a general framework for adversarial attacks on trained agents, which covers semantic perturbations to the environment of the agent performing the task as well as pixel-level attacks. To do this, we re-frame the adversarial attack problem as learning a distribution of parameters that always fools the agent. In the semantic case, our proposed adversary (denoted as BBGAN) is trained to sample parameters that describe the environment with which the black-box agent interacts, such that the agent performs its dedicated task poorly in this environment. We apply BBGAN on three different tasks, primarily targeting aspects of autonomous navigation: object detection, self-driving, and autonomous UAV racing. On these tasks, BBGAN can generate failure cases that consistently fool a trained agent.
dc.description.sponsorshipThis work was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research under Award No. RGC/3/3570-01-01.
dc.publisherAssociation for the Advancement of Artificial Intelligence (AAAI)
dc.relation.urlhttps://aaai.org/ojs/index.php/AAAI/article/view/6722
dc.rightsArchived with thanks to Proceedings of the AAAI Conference on Artificial Intelligence
dc.titleSADA: Semantic Adversarial Diagnostic Attacks for Autonomous Applications
dc.typeArticle
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentElectrical Engineering Program
dc.contributor.departmentVCC Analytics Research Group
dc.identifier.journalProceedings of the AAAI Conference on Artificial Intelligence
dc.conference.date2020
dc.conference.nameAAAI Conference on Artificial Intelligence
dc.conference.locationNew York, USA
dc.eprint.versionPublisher's Version/PDF
dc.identifier.volume34
dc.identifier.issue07
dc.identifier.pages10901-10908
pubs.publication-statusPublished
dc.identifier.arxivid1812.02132
kaust.personHamdi, Abdullah
kaust.personMueller, Matthias
kaust.personGhanem, Bernard
kaust.grant.numberRGC/3/3570-01-01
refterms.dateFOA2020-08-12T06:50:11Z
kaust.acknowledged.supportUnitOffice of Sponsored Research


Files in this item

Thumbnail
Name:
SADA_AAAI.pdf
Size:
1.926Mb
Format:
PDF
Description:
Main article

This item appears in the following Collection(s)

Show simple item record