Fusion of Multi-Modal Credentials for Authentication in Digital Identity Management Systems

Abstract

The recent years have seen an increase in identity fraud and accessing online services when communication devices such as computers, mobile phones and card based credentials (e.g. credit cards) are involved. This has prompted most governments and business organizations to change the way they do business and manage the user's identity information. However Internet users are vulnerable to identity fraud, which is on the increase and costing the global economy excessive amounts. With the advent of wireless technologies, peer-to-peer communication, GSM networks, it is becoming more challenging to build systems to authenticate users more efficiently. Traditional methods of authenticating a user with passwords and PIN numbers only are slowly proving ineffective since these credentials are easy to guess and steal. This paper proposes a distributed multimodal authentication system as a solution for managing digital identity information on most wireless networks. The proposed system uses artificial intelligence methods and biometrics to improve the security and privacy of users and service providers in a transparent, reliable and efficient way. The system is implemented using a technique of information fusion to combine the user's credentials for optimum recognition and authentication.