Type2Branch: Keystroke Biometrics based on a Dual-branch Architecture with Attention Mechanisms and Set2set Loss

TL;DR

Type2Branch is a novel keystroke verification model that combines dual-branch architecture, attention mechanisms, and a new loss function to achieve state-of-the-art accuracy on large-scale datasets.

Contribution

It introduces a dual-branch architecture with attention and a Set2set loss, along with synthesized features and curriculum training, advancing keystroke biometrics verification at scale.

Findings

Achieves EERs of 0.77% and 1.03% on large desktop and mobile datasets.

Outperforms previous methods significantly in verification accuracy.

Provides publicly available code and dataset tools.

Abstract

In 2021, the pioneering work TypeNet showed that keystroke dynamics verification could scale to hundreds of thousands of users with minimal performance degradation. Recently, the KVC-onGoing competition has provided an open and robust experimental protocol for evaluating keystroke dynamics verification systems of such scale. %, including considerations of algorithmic fairness. This article describes Type2Branch, the model and techniques that achieved the lowest error rates at the KVC-onGoing, in both desktop and mobile typing scenarios. The novelty aspects of the proposed Type2Branch include: i) synthesized timing features emphasizing user behavior deviation from the general population, ii) a dual-branch architecture combining recurrent and convolutional paths with various attention mechanisms, iii) a new loss function named Set2set that captures the global structure of the embedding space, and iv) a training curriculum of increasing difficulty. Considering five enrollment samples per subject of approximately 50 characters typed, the proposed Type2Branch achieves state-of-the-art performance with mean per-subject Equal Error Rates (EERs) of 0.77% and 1.03% on evaluation sets of respectively 15,000 and 5,000 subjects for desktop and mobile scenarios. With a fixed global threshold for all subjects, the EERs are respectively 3.25% and 3.61% for desktop and mobile scenarios, outperforming previous approaches by a significant margin. The source code for dataset generation, model, and training process is publicly available.