Multibiometric System for Internet of Things using Trust Management

Abstract

Biometric-based authentication systems are prone to spoofing attacks, errors due to noisy data, intra- and inter-class variations. Combining multiple biometric traits (multibiometric system) promises more accuracy. However, this leads to overhead due to an increase in complexity, form factor, energy and latency in the system. In this paper, a trust management system is used together with a decision level multibiometric system to improve the accuracy and lower the energy consumption of the proposed system. The proposed system is found to drop the false positive rate value by a factor of 4 and the energy consumption was reduced by a factor of 7.