Towards Implicit Enhancement of Security and User Authentication in Mobile Devices Based on Movement and Audio Analysis
Hamed Ketabdar, Mehran Roshandel, Daria Skripko · 2011
Abstract—In this work, we present initial investigations towards analysing movements of a mobile device as well as ambient audio captured by the mobile device for enhancing security functionalities in the device. We present a few scenarios which can lead to security threats related to data or services on a mobile device (e.g., a phone being lost or stolen). We show how unexpected movements or ambient audio captured by the device can deliver information which can be important considering security issues, and reveal those scenarios. In addition, we present how the identity of a user can be verified (or identified) by his mobile device based on pattern of his regular physical activities such as walking. This allows for implicit and continuous re-identification of the user. The implicit process does not require active participation of user, and allows for authentication during regular daily activities. The proposed method can also be used to complement regular authentication techniques to protect for example an open account on a mobile phone. It can also help to reduce number of re-authentications by verifying that the mobile device is continuously operated by the same user since the last regular authentication. Our final goal is to come up with a correlation model describing the relationship between movements of a mobile device as well as ambient audio, and security related issues.