Siamese Networks for Static Keystroke Dynamics Authentication

Abstract

Keystroke dynamics authentication aims at recognizing individuals on their way of typing on a keyboard. It suffers from a high intra-class variability as any behavioral biometric modality; to provide a large quantity of enrollment samples often overcomes this issue.In this paper, we analyze the feasibility of using siamese networks to rely on biometric samples provided by other users instead of requesting a new user to provide a large number of enrollment samples. Such networks aim at comparing two inputs to compute their similarity: the authentication process consists then at comparing the query to an enrollment sample.The proposed method is compared to several compatible baselines in the literature. Its EER outperforms the best baseline of 28% in a oneshot context and 31% when using 200 enrollment samples. This proves the viability of such approach and opens the path to improvements for using it in other contexts of keystroke dynamics authentication.