Enhancing a fog-oriented IoT authentication and encryption platform through deep learning-based attack detection

Abstract

The term Internet of Things (IoT) refers to a network that connects smart things with sensors. Healthcare, transportation, and smart cities are some IoT applications. IoT technologies integrate objects in the cloud-based Internet. The massive scale of IoT exposes some systems to attacks. There is an urgent need for solutions that efficiently handle IoT authentication, encryption, and attack detection. This work proposes a Fog-based IoT security platform named IoTSafe. It contains mechanisms for authentication and encryption and a deep learning-based attack detection module. The IoTSafe attack detection module uses the Message Queue Telemetry Transport (MQTT). Tests were performed to evaluate the IoTSafe platform in three different environments. A case study demonstrated that the platform is efficient with all proposed mechanisms and modules. The results for the attack detection module show the proposal’s effectiveness with an accuracy of 99.57% and a precision of 99.66%. The IoTSafe time response was less than one second, guaranteeing the quality of service.