Deepauth: In-Situ Authentication for Smartwatches via Deeply Learned Behavioural Biometrics

Chris Xiaoxuan Lu, Bowen Du, Peijun Zhao, Hongkai Wen, Yiran Shen, Andrew Markham, Niki Trigoni

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper proposes DeepAuth, an in-situ authentication framework that leverages the unique motion patterns when users entering passwords as behavioural biometrics. It uses a deep recurrent neural network to capture the subtle motion signatures during password input, and employs a novel loss function to learn deep feature representations that are robust to noise, unseen passwords, and malicious imposters even with limited training data. DeepAuth is by design optimised for resource constrained platforms, and uses a novel split-RNN architecture to slim inference down to run in real-time on off-the-shelf smartwatches. Extensive experiments with real-world data show that DeepAuth outperforms the state-of-the-art significantly in both authentication performance and cost, offering real-time authentication on a variety of smartwatches.
Original languageEnglish
Title of host publicationProceedings of the 2018 ACM International Symposium on Wearable Computers
Place of PublicationNew York, NY, USA
PublisherACM Association for Computing Machinery
Pages204–207
Number of pages4
ISBN (Print)9781450359672
DOIs
Publication statusPublished - 8 Oct 2018
Event2018 ACM International Symposium on Wearable Computers - Suntec Singapore Convention and Exhibition Center, Singapore
Duration: 8 Oct 201812 Oct 2018
http://iswc.net/iswc18/index.html

Publication series

NameISWC '18
PublisherAssociation for Computing Machinery

Symposium

Symposium2018 ACM International Symposium on Wearable Computers
Abbreviated titleISWC 2018
Country/TerritorySingapore
Period8/10/1812/10/18
Internet address

Keywords

  • security
  • split-RNN
  • authentication
  • smartwatch

Fingerprint

Dive into the research topics of 'Deepauth: In-Situ Authentication for Smartwatches via Deeply Learned Behavioural Biometrics'. Together they form a unique fingerprint.

Cite this