Adversarial training to prevent wake word jamming in Personal Voice Assistants

Simple item page
dc.contributor.authorSagi, Prathyushaen
dc.contributor.authorSankar, Arunen
dc.contributor.authorRoedig, Utzen
dc.contributor.funderScience Foundation Irelanden
dc.date.accessioned2024-05-28T10:52:15Z
dc.date.available2024-05-28T10:52:15Z
dc.date.issued2024-05en
dc.description.abstractWake word detection algorithms in Personal Voice Assistants (PVAs) are not designed to handle acoustic Denial of Service (DoS) attacks. We show that adversarial training can be used to improve the resilience of wake word detection against jamming attacks. We demonstrate that the inclusion of jammed wake word samples (adversarial samples) in the training phase of a wake word detection algorithm can defeat jamming attacks. The careful selection of the jamming signal type used during training ensures that wake word recognition is also resilient against jamming signals unknown during training; defeating a priori unknown jamming signal types is possible. We optimize the adversarial training effort by identifying areas of the wake word that are highly susceptible to acoustic interference, which guides our generation of adversarial training samples. We demonstrate the success of the proposed approach using a variety of wake words and two different wake word detection algorithms.en
dc.description.sponsorshipScience Foundation Ireland (13/RC/2077 P2)en
dc.description.statusPeer revieweden
dc.description.versionAccepted Versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.citationSagi, P., Sankar, A. and Roedig, U. (2024) 'Adversarial training to prevent wake word jamming in Personal Voice Assistants', 20th International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT 2024), Abu Dhabi, United Arab Emirates, 29 April - 1 May 2024. https://doi.org/10.1109/DCOSS-IoT61029.2024.00018en
dc.identifier.doi10.1109/DCOSS-IoT61029.2024.00018
dc.identifier.eissn2325-2944
dc.identifier.issn2325-2936
dc.identifier.urihttps://hdl.handle.net/10468/15924
dc.language.isoenen
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.relation.ispartof20th International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT 2024), Abu Dhabi, United Arab Emirates, 29 April - 1 May 2024.en
dc.relation.projectinfo:eu-repo/grantAgreement/SFI/SFI Frontiers for the Future::Award/19/FFP/6775/IE/Personal Voice Assistant Security and Privacy/en
dc.rights© 2024, IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.en
dc.subjectPersonal Voice Assistant (PVA)en
dc.subjectWake word detectionen
dc.subjectAcoustic jammingen
dc.subjectAdversarial trainingen
dc.titleAdversarial training to prevent wake word jamming in Personal Voice Assistantsen
dc.typeConference itemen
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Adversarial Training to Prevent Wake Word Jamming in Personal Voice Assistants.pdf
Size:
3.5 MB
Format:
Adobe Portable Document Format
Description:
Accepted Version
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
2.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Computer Science - Conference Items