A Survey of behavioral authentication using keystroke dynamics: Touch screens and mobile devices

Abstract

Nowadays most systems became computerized and use internet for remote access, including systems which have critical and sensitive data such as banks and governmental institutions. This led to the huge need for a reliable and efficient authentication system to secure data. User authentication is mostly done using passwords. But it is not a sufficient way to use just a password since it has many drawbacks, like guessing them, brute force attacks, key-loggers and social engineering. Additional authentication procedure is needed to enhance password security. Keystroke dynamics is one of the famous behavioral measurements that rely on utilizing the typing rhythm of each individual. It is used to strengthen password authentication in an efficient and cheap way since no hardware will be added. This paper presents a comprehensive survey on research in the last two decades on keystroke dynamics authentication. The objective is to discuss, summarize and provide insightful comparison about the well-known approaches used in keystroke dynamics such as statistical and neural network approaches, as well as offering suggestions and possible future research directions, especially for touch-screen and mobile devices. Keystroke dynamics could provide a second authentication factor for touch screen devices, as they are rapidly increasing in their use and are replacing the classical keyboards in the markets.