Differentiated Security in the Age of Cognitive Internet of Things (CIoT)

Our IoT systems are transforming from “perceptive” to “cognitive,” where connected IoT devices behave as agents and interact with each other in a context-aware manner with minimum human intervention, learning from both the physical environment and experience. New security challenges surface as IoT applications are empowered with more cognitive capability. The vast amount of ever-growing data needed to equip our devices with artificial intelligence puts enormous pressure on the protection of sensitive data flow and the efficiency of network resource utilization. In order to address the potential security challenges for cognitive IoT systems, we first drafted a survey to study the security requirements and challenges of recent IoT proposals for future smart cities and then proposed a differentiated security architecture that enhances security and efficiency for data communication. In the future, we aim to build an incentive mechanism to encourage secure peer-to-peer data sharing using our proposed differentiated security architecture and deep learning techniques.