IoT Security Based on Iris Verification Using Multi-Algorithm Feature Level Fusion Scheme

Internet of Things (IoT) have very big opportunities in businesses and life, especially Internet Banking, Healthcare and Transportation. But developers face challenges in security especially for sensitive data to use IoT safely with Internet Banking. In this paper, a secure IoT connection between clients and broker server based on iris recognition system (Authentication server) will be proposed. The proposed iris recognition system will communicate with MQTT broker server to increase authentication instead of using normal text method (username/password). The proposed authentication server in this paper is to use iris as uni-modal biometric trait, by applying different scenarios of multi-biometrics other than the multimodal, to develop and implement iris-based recognition system. In feature extraction phase, the fusion between vectors of Delta-Mean (DM) and Multi-Algorithm-Mean (MAM) executed in a parallel mode. Then, followed by the proposed reduction method, reduced the feature vector size keeping higher performance. Finally, classification is adopted by using Euclidian Distance (ED) classifier. It is suitable for secure MQTT connection message to authenticate right client in sensitive application like bank transfer operations.