Client-agnostic continuous authentication via keystroke-induced traffic patterns

How can we continuously verify the identity of users without modifying their devices? We introduce a client–agnostic method that leverages keystroke–induced network traffic patterns to passively authenticate users. It can be deployed on infrastructure already common in network environments. By applying contrastive learning to Web–Socket packet traces, we compare new traffic against previously seen patterns from the same user. In an experiment with 75 users, our method achieved 87% accuracy — improving over a statistical baseline by 27.7 percentage points (pp). These results demonstrate that network traffic captures meaningful behavioral signatures and can serve as a foundation for practical, continuous user authentication.

Metadaten
Author:	Alexander Niedermayer, David Monschein, Oliver P. Waldhorst
URN:	urn:nbn:de:bvb:384-opus4-1252615
Frontdoor URL	https://opus.bibliothek.uni-augsburg.de/opus4/125261
Parent Title (English):	3rd Workshop on Machine Learning in Networking (MaLeNe), co-located with the 6th International Conference on Networked Systems (NetSys 2025), Ilmenau, Germany, September 1, 2025: proceedings
Publisher:	Universität Augsburg
Place of publication:	Augsburg
Editor:	Michael SeufertORCiD GND, Andreas Blenk, Björn Richerzhagen
Type:	Conference Proceeding
Language:	English
Date of Publication (online):	2025/09/15
Year of first Publication:	2025
Publishing Institution:	Universität Augsburg
Release Date:	2025/09/16
Institutes:	Fakultät für Angewandte Informatik
	Fakultät für Angewandte Informatik / Institut für Informatik
	Fakultät für Angewandte Informatik / Institut für Informatik / Lehrstuhl für Vernetzte Systeme und Kommunikationsnetze
Dewey Decimal Classification:	0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik
Licence (German):	CC-BY 4.0: Creative Commons: Namensnennung (mit Print on Demand)

Open Access