Anomaly detection through keystroke and tap dynamics implemented via machine learning algorithms

Abstract

In our world of growing machine intelligence and increasing security risks, there is a dire need for authentication to be liberated from password dependency and restrictions. This paper discusses the implementation of keystroke biometrics to enhance security using machine-learning algorithms on both Windows and Android. Our research analyzes a user's behavior for authorization purposes by capturing the user's typing pattern. The system extracts several features from the user's typing pattern to apply unary classification for user behavior analysis so that we can detect unauthorized users. Our system implements machine learning on tap dynamics in Android, allowing both training and prediction and overcoming its computational restrictions.