DEVELOPMENT OF A MULTI-LEVEL SECURITY MODEL FOR MOBILE PAYMENT SYSTEM

Abstract

The emergence of mobile commerce has created new financial needs that in many cases cannot be effectively fulfilled by the traditional payment systems. In mobile payments, the core is authentication, which is a critical concern in mobile wireless environment. In traditional authentication methods, authentication is based on “what you know”, such as passwords or PINs, and “what you have” such as tokens. The user of a mobile device would be admitted access when he/she input a correct password or tap a genuine token. However, both methods suffer some weaknesses. First, passwords are hard to be managed. A short password is easy to recall but also easy to be guessed or broken down by the adversary via brute force attacks. While a long password can provide strong security, it is difficult to remember, especially when there are different passwords for different accounts. Second, tokens can be lost or stolen. Most importantly, both methods cannot tell whether a presenter of the password or token is the genuine user or not. Hence, this research work developed a multi-level security model for mobile payment system using Support Vector Machine (SVM). The research work involves user enrollment, authentication and the payment processing. Face detection was carried out using the Viola and Jones algorithm, Face recognition was carried out using SVM and user’s data was encrypted using Rivest- Shamir- Adleman (RSA) algorithm. The evaluation of the result obtained showed Viola Jones + SVM + RSA had performed better with 0.90 accuracy, 0.923 recall, and 0.1 F1-Score. The model when compared with other facial recognition algorithms shows significant impact on security of mobile payment system