Context-Aware Mobile Biometric Authentication based on Support Vector Machines

Abstract

The ubiquitous use of smartphones raises the need for stronger device protection. Traditional authentication methods on mobile devices are still knowledge-based, exhibiting well- known drawbacks. In addition, requests for passwords, PINs, or screen lock patterns represent an interruption of the device usage. In this paper a context-aware mobile biometric system is proposed. Modern smartphone devices comprise a multitude of sensors which can be utilized to measure a variety of environmental aspects, e.g. noise level or location. Based on this contextual information subject-specific context models are constructed in order to train SVMs, providing an alternative user-friendly authentication mechanism. In experiments a self- acquired database is employed where obtained results confirm the feasibility of the proposed system.