Towards Keystroke Continuous Authentication Using Time Series Analytics

Abstract

An approach to Keystroke Continuous Authentication (KCA) is described founded on a time series analysis based approach that, unlike previous work on KCA (using feature vector representations), takes the sequencing of keystrokes into con- sideration. The significance of KCA is in the context of online assessments and examinations used in eLearning environments and MOOCs, which are becoming increasingly popular. The process is fully described and analysed, including compar- ison with established feature vector approaches. Our proposed method outperforms these other approaches to KCA (with a detection accuracy of 94%, compared to 79.53%), a clear indicator that the proposed time series analysis based KCA has significant potential.