Enhancing Free Text Keystroke Authentication with GAN-Optimized Deep Learning Classifiers

Jonathan A. Bazan, Katerina Potika () and Petros Potikas
Additional contact information
Jonathan A. Bazan: San Jose State University
Katerina Potika: San Jose State University
Petros Potikas: National Technical University of Athens

A chapter in Machine Learning, Deep Learning and AI for Cybersecurity, 2025, pp 623-647 from Springer

Abstract: Abstract Leveraging machine learning for biometric authentication is an area of research that has seen a lot of progress within the past decade. Keystroke authentication based on machine and deep learning binary classifiers aims to develop a robust model to distinguish a user from an adversary based on typing metrics (keystrokes). While keystroke authentication started with fixed text, where users types the same data, the shift has been to free text data where every user’s data varies. However, popular deep learning classifiers are bottlenecked by the large amount of data needed to make them efficient. This work solves the data bottleneck issue in keystroke authentication’s binary classification problem by utilizing Generative Adversarial Networks to generate free text keystroke data with a valid label. Furthermore, the produced synthetic data are used to train a Convolutional Neural Network, attempting to push the Equal Error Rate rate even lower and at the same time resolve the data bottleneck.

Date: 2025
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-031-83157-7_22

Ordering information: This item can be ordered from
http://www.springer.com/9783031831577

DOI: 10.1007/978-3-031-83157-7_22

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().