Site Search
Computer Science

Photos

Alioune Ngom, Ph.D.Dr. Alioune Ngom
Dr. Alioune Ngom
Dr. Scott GoodwinDr. Scott Goodwin
Dr. Scott Goodwin
Christie Ezeife, Ph.D.Dr. Christie Ezeife
Dr. Christie Ezeife
Arunita Jaekel, Ph.D.Dr. Arunita Jaekel
Dr. Arunita Jaekel
Imran Ahmad, Ph.D.Dr. Imran Ahmad
Dr. Imran Ahmad
Jessica Chen, Ph.D.Dr. Jessica Chen
Dr. Jessica Chen
Dr. Robert KentDr. Robert Kent
Dr. Robert Kent
Windsor WaterfrontWindsor Waterfront Park
Windsor Waterfront Park
Xiaobu Yuan, Ph.D.Dr. Xiaobu Yuan
Dr. Xiaobu Yuan
Dr. Ziad Kobti lecturingDr. Ziad Kobti
Dr. Ziad Kobti
Robin Gras, Ph.D.Dr. Robin Gras
Dr. Robin Gras
Dr. Luis RuedaDr. Luis Rueda
Dr. Luis Rueda
Lambton TowerLambton Tower
Lambton Tower

Identification of User Behavioral Biometrics for Authentication using Keystroke Dynamics and Machine Learning

Add this event into your calendar using the iCAL format
  • Tue, 04/17/2018 - 10:00am - 11:30am




 

Identification of User Behavioral Biometrics for Authentication using Keystroke Dynamics and Machine Learning

MSc Thesis Defense by:

Sowndarya Krishnamoorthy

Date:  Tuesday, April 17, 2018
Time:  10:00 am – 11:30 am
Location: 3105, Lambton Tower

Abstract: This thesis focuses on the effective classification of the behavior of users accessing computing devices to authenticate them. The authentication is based on keystroke dynamics which captures the users behavioral biometric and applies machine learning concepts to classify them. To handle the multi-class problem, random forest classifier is used to identify the users effectively. The mRMR feature selection has been applied to increase the classification performance metrics and to confirm the identity of the users based on the way they access computing devices. From the results, we conclude that device information and touch pressure effectively contribute to identifying each user. Out of them, features which contain device information are responsible for increasing the performance metrics of the system by adding a token-based authentication layer. Based upon the results, random forest yields better classification results for this dataset. The research will contribute significantly to the field of cyber-security by forming a robust authentication system using machine learning algorithms.

Thesis Committee:
Internal Reader:  Dr. Sherif Saad     
External Reader:  Dr. Gokul Bhandari
Advisor:  Dr. Luis Rueda
Chair:  Dr. Dan Wu  



csgradinfo@uwindsor.ca
(519)253-3000


See More: