Keystroke dynamics using auto encoders

Patel, Yogesh, Ouazzane, Karim, Vassilev, Vassil, Faruqi, Ibrahim and Walker, George L. (2019) Keystroke dynamics using auto encoders. In: Cyber Security 2019: International Conference on Cyber Security and Protection of Digital Services, 3-4 June 2019, University of Oxford.

Abstract

In the modern day and age, credential based authentication systems no longer provide the level of security that many organisations and their services require. The level of trust in passwords has plummeted in recent years, with waves of cyber attacks predicated on compromised and stolen credentials. This method of authentication is also heavily reliant on the individual user’s choice of password. There is the potential to build levels of security on top of credential based authentication systems, using a risk based approach, which preserves the seamless authentication experience for the end user. One method of adding this security to a risk based authentication framework, is keystroke dynamics. Monitoring the behaviour of the users and how they type, produces a type of digital signature which is unique to that individual. Learning this behaviour allows dynamic flags to be applied to anomalous typing patterns that are produced by attackers using stolen credentials, as a potential risk of fraud. Methods from statistics and machine learning have been explored to try and implement such solutions. This paper will look at an Autoencoder model for learning the keystroke dynamics of specific users. The results from this paper show an improvement over the traditional tried and tested statistical approaches with an Equal Error Rate of 6.51%, with the additional benefits of relatively low training times and less reliance on feature engineering.

Documents
4803:24372
[img]
Preview
PID5872685_camera-ready_Oxford_IEEE_conference.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (676kB) | Preview
Details
Record
Statistics

Downloads

Downloads per month over past year



Downloads each year

View Item View Item