Mouse Dynamics Analysis Using Machine Learning to Prevent Account Stealing in Web Systems

This paper is dedicated to development of algorithm of website users authentication based on their mouse movement dynamics. The algorithm of mouse activity data collection, feature extraction and mouse dynamics sessions classification to legal and illegal ones using machine learning and deep learnin...

Full description

Bibliographic Details
Main Authors: Alexey G. Marakhtanov, Evgeny O. Parenchenkov, Nikolai V. Smirnov
Format: Article
Language:English
Published: FRUCT 2022-04-01
Series:Proceedings of the XXth Conference of Open Innovations Association FRUCT
Subjects:
Online Access:https://www.fruct.org/publications/fruct31/files/Mar.pdf
Description
Summary:This paper is dedicated to development of algorithm of website users authentication based on their mouse movement dynamics. The algorithm of mouse activity data collection, feature extraction and mouse dynamics sessions classification to legal and illegal ones using machine learning and deep learning methods is proposed. The user authentication problem is considered as one-class classification and binary classification problem. The performance of the algorithm is evaluated on mouse dynamics dataset gathered on a public website.
ISSN:2305-7254
2343-0737