SetMargin Loss applied to Deep Keystroke Biometrics with Circle Packing Interpretation

TL;DR

This paper introduces SetMargin Loss, a novel deep learning method for keystroke biometrics that enhances class separation in learned representations, achieving state-of-the-art accuracy on a large-scale dataset.

Contribution

The paper proposes SetMargin Loss, a new Distance Metric Learning approach guided by set pairs and analyzed through Circle Packing, specifically designed for free-text keystroke identification.

Findings

Achieves state-of-the-art accuracy on 78,000 subjects

Enlarges inter-class distances while preserving intra-class structure

Effectively handles free-text keystroke identification

Abstract

This work presents a new deep learning approach for keystroke biometrics based on a novel Distance Metric Learning method (DML). DML maps input data into a learned representation space that reveals a "semantic" structure based on distances. In this work, we propose a novel DML method specifically designed to address the challenges associated to free-text keystroke identification where the classes used in learning and inference are disjoint. The proposed SetMargin Loss (SM-L) extends traditional DML approaches with a learning process guided by pairs of sets instead of pairs of samples, as done traditionally. The proposed learning strategy allows to enlarge inter-class distances while maintaining the intra-class structure of keystroke dynamics. We analyze the resulting representation space using the mathematical problem known as Circle Packing, which provides neighbourhood structures with a theoretical maximum inter-class distance. We finally prove experimentally the effectiveness of the proposed approach on a challenging task: keystroke biometric identification over a large set of 78,000 subjects. Our method achieves state-of-the-art accuracy on a comparison performed with the best existing approaches.