Mouse Dynamics Behavioral Biometrics: A Survey
Simon Khan, Charles Devlen, Michael Manno, Daqing Hou
TL;DR
The paper addresses the security limitations of password-based authentication by surveying behavioral biometrics, focusing on mouse dynamics and widget interactions from 1897 to 2023. It systematically analyzes data collection tasks, raw data types, feature definitions, public datasets, algorithmic approaches (statistical, ML, and deep learning), data fusion, and performance, while examining spoofing threats. It provides a taxonomy of experimental settings, catalogs public datasets (e.g., Balabit, ISOT, Minecraft), and reviews deep-learning and multimodal fusion techniques that enhance authentication robustness. The findings reveal data-quality and benchmarking gaps, highlight the potential of incorporating established HCI psychology models (such as $I_d$ and $I_p$ from Fitts' law) into feature design, and outline opportunities to extend to trackpads and touch devices for practical deployment.
Abstract
Utilization of the Internet in our everyday lives has made us vulnerable in terms of privacy and security of our data and systems. Therefore, there is a pressing need to protect our data and systems by improving authentication mechanisms, which are expected to be low cost, unobtrusive, and ideally ubiquitous in nature. Behavioral biometric modalities such as mouse dynamics (mouse behaviors on a graphical user interface (GUI)) and widget interactions (another modality closely related to mouse dynamics that also considers the target (widget) of a GUI interaction, such as links, buttons, and combo-boxes) can bolster the security of existing authentication systems because of their ability to distinguish an individual based on their unique features. As a result, it can be difficult for an imposter to impersonate these behavioral biometrics, making them suitable for authentication. In this paper, we survey the literature on mouse dynamics and widget interactions dated from 1897 to 2023. We begin our survey with an account of the psychological perspectives on behavioral biometrics. We then analyze the literature along the following dimensions: tasks and experimental settings for data collection, taxonomy of raw attributes, feature extractions and mathematical definitions, publicly available datasets, algorithms (statistical, machine learning, and deep learning), data fusion, performance, and limitations. Lastly, we end the paper with presenting challenges and promising research opportunities.