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
