Visible to the public Deepauth: In-situ Authentication for Smartwatches via Deeply Learned Behavioural Biometrics

TitleDeepauth: In-situ Authentication for Smartwatches via Deeply Learned Behavioural Biometrics
Publication TypeConference Paper
Year of Publication2018
AuthorsLu, Chris Xiaoxuan, Du, Bowen, Zhao, Peijun, Wen, Hongkai, Shen, Yiran, Markham, Andrew, Trigoni, Niki
Conference NameProceedings of the 2018 ACM International Symposium on Wearable Computers
Conference LocationNew York, NY, USA
ISBN Number978-1-4503-5967-2
Keywordsauthentication, Human Behavior, Pervasive Computing Security, pubcrawl, Resiliency, Scalability, security, smartwatch, split-RNN, wearables security

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.

Citation Keylu_deepauth:_2018