Adaptive techniques for intra-user variability in keystroke dynamics

Conventional machine learning algorithms based on keystroke dynamics build a classifier from labeled data in one or more sessions but assume that the dataset at the time of verification exhibits the same distribution. A user's typing characteristics may gradually change over time and space. Therefore, a traditional classifier may perform poorly on another dataset that is acquired under different environmental conditions. In this paper, we investigate the applicability of transfer learning to update a classifier according to the changing environmental conditions with minimum amount of re-training. We show that by using adaptive techniques, it is possible to identify an individual at a different time by acquiring only a few samples from another session, and at the same time obtain up to 13% higher accuracy. We make a comparative analysis among the proposed algorithms and conclude that adaptive classifiers exhibit a higher start by a good approximation and perform better than the classifier trained from start-over.