DADA: Dynamic authenticator for data access

Huang, Chenyang

Permalink

https://hdl.handle.net/2142/116259 Copy

Description

Title

DADA: Dynamic authenticator for data access

Author(s)

Huang, Chenyang

Issue Date

2022-07-20

Director of Research (if dissertation) or Advisor (if thesis)

Kalbarczyk, Zbigniew T

Department of Study

Electrical & Computer Eng

Discipline

Electrical & Computer Engr

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

M.S.

Degree Level

Thesis

Keyword(s)

• Security
• Authentication
• Behavioral Biometrics Authentication
• Recurrent Neural Networks
• Electronic Medical Record (EMR)
• Data Engineering
• Machine Learning
• User Identification

Abstract

Traditional authentication models for data access are vulnerable to prevalent attack vectors: insider attack, where one or more of the attackers is a genuine user that has proper access to the system; Hacking, where the attackers ac quire the credentials of a legitimate user in the system; Trojan attack, where the attackers injects malicious scripts on legitimate users’ computers. The Multi-Factor-Authentication scheme has gained much popularity in recent years. It remedies the shortcomings of password-based authentication, but is cumbersome and does not fully solve the problem with insider attack. In this study, we explore an approach to authenticate users based on what they do, rather than what they know. By monitoring users’ data access patterns, we show that it is possible to authenticate future access requests by checking if they conform to the established data access behavior pattern of the user.

Graduation Semester

2022-08

Type of Resource

Thesis

Copyright and License Information

© 2022 ChenYang Huang

Owning Collections