Multi-factor behavioral authentication based on webpage platform using combined data sources

Behavioral biometrics have been widely considered useful for user authentication. Behavioral biometrics include, but are not limited to, browser history, mouse dynamics, keystroke dynamics, GPS location, and so on. In this research, we focus on building a combined behavioral biometric authentication method based on a web platform where we collect users’ keystrokes, mouse movements, and interaction with the platform. For each of the data source, we build a neural network to authenticate the user. We then combine the networks together to reach a better accuracy of user authentication. The research aims to develop an authentication method that identify the user by studying behavioral data generated from webpage interactions, which would be difficult to hack and can be used while authentication methods such as passwords and facial recognition are vulnerable during attacks.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Electrical & Computer Engr

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2022

Author dc:creator

• Ren, Yuhang

Contributors dc:contributor

• Hu, Yih-Chun

• Behavioral Biometrics
• Multi-factor Authentication

Statement dc:rights

• Copyright 2022 Yuhang Ren

Language dc:language

en, eng

Handle dc:identifier

https://hdl.handle.net/2142/117606

OAI record oai:identifier

https://www.ideals.illinois.edu/oai-pmh?verb=GetRecord&metadataPrefix=etdms&identifier=oai%3Awww.ideals.illinois.edu%3A2142%2F117606