Knock-to-Enter Authentication : A Rhythm-Based Smartphone Authentication Mechanism

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

View graph of relations

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationIECON 2023- 49th Annual Conference of the IEEE Industrial Electronics Society
PublisherIEEE
ISBN (Electronic)979-8-3503-3182-0
ISBN (Print)979-8-3503-3183-7
Publication statusPublished - 2023

Publication series

NameIECON Proceedings (Industrial Electronics Conference)
ISSN (Print)1553-572X
ISSN (Electronic)2577-1647

Conference

Title49th Annual Conference of the IEEE Industrial Electronics Society (IECON 2023)
LocationMarina Bay Sands Expo and Convention Centre
PlaceSingapore
Period16 - 19 October 2023

Abstract

With 2-factor authentication practices becoming ever more popular, the need for developing new authentication procedures is gaining ever more traction. Rhythm-based gesture authentication appears to be a promising area of research as it encompasses two of the three main authenticator factors: something you know(the chosen rhythm) and something you are(how you enter that rhythm). Rhythm-based authentication approaches have mostly been achieved using touchscreen functions. But accelerometers and gyroscope sensors have the unique ability to capture the small differences in how users enter a set rhythm and how they hold their phone. Additionally, these sensors do not limit our approach to mobile devices with mobile screens but can be expanded to headsets, smart glasses, and screen-less fitness trackers. It also circumvents issues like wearing face masks and gloves. All 12 of our participants were asked to input the same tapping rhythm consisting of 7 taps, 50 times, totaling 600 samples to be used for trial and testing. If our system is able to perform well under these conditions it proves that even an attacker who knows your rhythm, wouldn't be able to access your device. This could be equated to you telling someone your password, but them still not being able to gain access to your phone. Our models were able to achieve an authentication accuracy of 99.65% only using 10 valid samples for training and an identification accuracy of 99.17 %. © 2023 IEEE.

Research Area(s)

  • Behavioral Biometrics, Gesture Authentication, Smart Wearable Device

Citation Format(s)

Knock-to-Enter Authentication: A Rhythm-Based Smartphone Authentication Mechanism. / Boshoff, Dutliff; Nkrow, Raphael; Hancke, Gerhard P.
IECON 2023- 49th Annual Conference of the IEEE Industrial Electronics Society. IEEE, 2023. (IECON Proceedings (Industrial Electronics Conference)).

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review