Rakshit Gupta

Publication Date

Spring 2024

Degree Type

Master's Project

Degree Name

Master of Science in Computer Science (MSCS)


Computer Science

First Advisor

Fabio Di Troia

Second Advisor

William Andreopoulos

Third Advisor

Ching-Seh Wu


Behavioral Biometrics, Mouse Dynamics, CNN, LSTM, Transformer models, Multiclass Classification


User authentication and identification plays a crucial role in ensuring the security and integrity of digital systems. Traditional authentication methods, such as passwords and biometrics, have inherent limitations that can compromise system security. This research proposes a novel approach to user authentication by leveraging machine learning techniques and behavioral biometrics, specifically mouse dynamics. The primary objective is to develop a sophisticated framework that can accurately identify individuals based on their unique mouse behavior patterns. The study explores and compares multiple deep learning architectures, including Convolutional Neural Networks (CNN), Long Short-Term Memory networks (LSTM), and Transformer models, to generate embeddings from time-series data extracted from user sessions. These embeddings are then utilized for multiclass classification, treating user authentication as a multiclass problem rather than a binary classification task commonly seen in prior research.

The research employs the Balabit Mouse Dynamics Challenge Dataset to investi- gate the efficacy of different deep learning architectures in creating embeddings from temporal user session data and their subsequent performance in accurately classifying users based on mouse dynamics. The study highlights the enhancements made by the proposed framework by delivering a comparative analysis with the existing research.

Available for download on Friday, May 23, 2025