Continuous Authentication on Mobile Devices by Analysis of Typing Motion Behavior

Hugo Gascon, Sebastian Uellenbeck, Christopher Wolf, Konrad Rieck

GI Si­cher­heit - Schutz und Zu­ver­läs­sig­keit, Jah­res­ta­gung des Fach­be­reichs Si­cher­heit der Ge­sell­schaft für In­for­ma­tik, Vienna, Austria, March 2014


Smartphones have become the standard personal device to store private or sensitive information. Widely used as every day gadget, however, they are susceptible to get lost or stolen. To protect information on a smartphone from being physically accessed by attackers, a lot of authentication methods have been proposed in recent years. Each one of them suffers from certain drawbacks, either they are easy to circumvent, vulnerable against shoulder surfing attacks, or cumbersome to use. In this paper, we present an alternative approach for user authentication that is based on the smartphone's sensors. By making use of the user's biometrical behavior while entering text into the smartphone, we transparently authenticate the user in an ongoing-fashion. In a field study, we asked more than 300 participants to enter some short sentences into a smartphone while all available sensor events were recorded to determine a typing motion fingerprint of the user. After the proper feature extraction, a machine learning classifier based on Support Vector Machines (SVM) is used to identify the authorized user. The results of our study are twofold: While our approach is able to continuously authenticate some users with high precision, there also exist participants for which no accurate motion fingerprint can be learned. We analyze these difference in detail and provide guidelines for similar problems.


Tags: authentication, machine learning, Mobile Security