User Authentication via Multifaceted Mouse Movements and Outlier Exposure

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearch

Authors

Gaining information about how users interact with systems is key to behavioural biometrics. Particularly mouse movements of users have been proven beneficial to authentication tasks for being inexpensive and non-intrusive. State-of-the-art approaches consider this problem an instance of supervised classification tasks. In this paper, we argue that the problem is actually closer to unsupervised one-class classification tasks. We thus propose to view behavioural user authentication as an unsupervised task and learn individual models using data from a single user only. We further show that, by being purely unsupervised, losses in performance can be counterbalanced by augmenting additional data into the training processes (outlier exposure). Empirical results show that our approach is very effective and outperforms the state-of-the-art in several performance metrics. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
Original languageEnglish
Title of host publicationAdvances in Intelligent Data Analysis XXI : 21st International Symposium on Intelligent Data Analysis, IDA 2023, Louvain-la-Neuve, Belgium, April 12–14, 2023, Proceedings
EditorsBruno Crémilleux, Sibylle Hess, Siegfried Nijssen
Number of pages14
Place of PublicationCham
PublisherSpringer Nature Switzerland AG
Publication date01.04.2023
Pages300-313
ISBN (print)978-3-031-30046-2
ISBN (electronic)978-3-031-30047-9
DOIs
Publication statusPublished - 01.04.2023
Event21st International Symposium on Intelligent Data Analysis - IDA 2023 - Louvain-la-Neuve, Belgium
Duration: 12.04.202314.04.2023
Conference number: 21
https://ida2023.org/

Bibliographical note

Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

    Research areas

  • Anomaly Detection, Mouse Dynamics, User Authentication, Authentication, Behavioral research, Mammals, Statistics, Supervised learning, Anomaly detection, Behavioural Biometric, Classification tasks, Mouse dynamics, Mouse movements, Non-intrusive, One-class Classification, State-of-the-art approach, Supervised classification, User authentication
  • Informatics