Multi-Modal Behavioural Biometric Authentication for Mobile Devices
Saevanee H, Clarke NL, Furnell SM
27th IFIP International Information Security and Privacy Conference - SEC2012
Heraklion, Crete, Greece, 4-6 June, pp465-474
The potential advantages of behavioural biometrics are that they can be util-ised in a transparent (non-intrusive) and continuous authentication system. However, individual biometric techniques are not suited to all users and scenar-ios. One way to increase the reliability of transparent and continuous authenti-cation systems is create a multi-modal behavioural biometric authentication sys-tem. This research investigated three behavioural biometric techniques based on SMS texting activities and messages, looking to apply these techniques as a multi-modal biometric authentication method for mobile devices. The results showed that behaviour profiling, keystroke dynamics and linguistic profiling can be used to discriminate users with overall error rates 20%, 20% and 22% respectively. To study the feasibility of multi-modal behaviour biometric au-thentication system, matching-level fusion methods were applied. Two fusion methods were utilised: simple sum and weight average. The results showed clearly that matching-level fusion can improve the classification performance with an overall EER 8%.
Sorry, this publication is not currently available to the public due to copyright restrictions.
We are unable to provide copies of this publication at present.
Centre for Security, Communications and Network Research (CSCAN), Room A304 Portland Square, Plymouth University, Plymouth, PL4 8AA, United Kingdom
Telephone: +44 (0) 1752 586234, Fax: +44 (0) 1752 586300, Email: firstname.lastname@example.org