PASSPHRASE AUTHENTICATION BASED ON TYPING STYLE THROUGH AN ART 2 NEURAL NETWORK

This study proposes the use of an artificial neural network algorithm to perform passphrase authentication based on the typing style of a user. The only hardware required is a keyboard. Prior studies have demonstrated the feasibility of this approach and its limitations, one of which was the need for collection of impostor samples for training the artificial neural network based classifier algorithm. This requirement is rather impractical for most application domains. The proposed study eliminates the need to collect impostor samples by employing an unsupervised and self-organizing artificial neural network algorithm, the Adaptive Resonance Theory 2 neural network, and therefore pushes the passphrase authentication technology one step closer to the realm of practical implementation. The preliminary study performed demonstrates that it is possible to train an Adaptive Resonance Theory 2 neural network using only authentic sample data and still provide a relatively low impostor pass rate. Given the minimal cost and easy in-field trainability of the proposed passphrase authentication system, the developed system can greatly enhance the security of computing environments with wide acceptance.