Keystroke Dynamics : Not What You Type But How You Type
Suraj S Shelke, Vidya Shinde, Sneha Pujar · International journal of advance research and innovative ideas in education · 2017
Nowadays data exposure is a source of growing concern due to the widespread use of internet. Most commonly used login and password credentials may not provide enough security, as they may be easily stolen or guessed in some cases. Global access to information and resources is becoming an integral part of nearly every aspect of our lives. All the data are stored across the globe and maintained by the cloud service providers as cloud computing is growing vastly due to its advantages. Unfortunately along with this comes increased chances of malicious attacks and intrusion. Security of the data is a major concern in terms of both outsiders and insiders. The use of biometrics is a prominent alternative for user authentication, such as by the use of keystroke dynamics. This biometric technology allows the recognition of users by their typing rhythm, which can be performed using data provided by a common keyboard. Keystroke dynamics is robust against forgery attacks as well as malware detection. However, recent work has shown that typing rhythm changes over time. The proposed approach uses a host based user profiling techniques where a keystroke dynamics used for analyzing the user behavior. Along with it a retraining approach is also proposed as imposter patterns are absent at the time of registration. This retraining phase enhances security and overall performance of the system.