Abstract:
This research investigates the use of the keystroke dynamics biometric as an added security for passwords and PINs (Personal Identification Numbers) used in POS (Points of Sale), banking Automatic Teller Machines (ATM) and credit cards. The research employs an algorithm using the keystroke dynamics which attempts to minimize compromising the security when an imposter gets hold of both the user-ID (user card) and the password.
Experiments were conducted using numeric passwords of varying length by a group of users.
The experimental results were encouraging for PINs of length 3-12 digits where the rate of rejection of legitimate users (FRR) was almost zero. However, reducing the rate of accepting an imposter (FAR) is the challenge. After implementing the experiment the results show that, by using the proposed method, FAR is reduced to 19.9% for PINs length greater than 3 digits.
The research reports the results of the experiments and recommends an optimum number of digits in passwords when this biometrics is used.
Based on experimental results and when using the probability of true rejection for each digit (TRPD) , a PIN of length of 4 digits (or when long PINs are divided to sub-key groups of 4 digits) was found to be the best.
