Using Artificial Intelligence for Trust Management Systems in Fog Computing: A Comprehensive Study

Fog computing has recently attracted great attention as an emerging computing paradigm, avoiding the latency concerns of the cloud. However, because of the distributed, decentralized nature of the fog, several security and privacy issues arise when fog nodes interact and exchange data in specific tasks. Fog servers must be trustworthy for delegation since they are close to the end user and can obtain sensitive information. Yet, normal cryptographic solutions cannot be used to control internal attacks, i.e., from a rogue node that has been authenticated to join the network, raising the concern of how to establish a trustworthy communication between the fog nodes. Trust Management Systems (TMS) have been developed to calculate the level of assurance between fog nodes based on their communication behavior to detect the rogue nodes in the network. Password-based, Traditional authentication methods, i.e., biometric-based and certificated-based, do not fit the fog because of its uniqueness architecture, consuming substantially additional processing power and provoking latency. Thus, several research issues remain open for TMS in the fog, including creating trusted execution environments, trust and security during fog orchestration, collusion attack and access control. In this paper, we investigate using artificial intelligence techniques to tackle the main challenges of TMS in fog computing. We conducted a comparative study to evaluate the major TMS in literature and identify their advantages and disadvantages. We then highlight 17 primary insights and recommendations to improve TMS using artificial intelligence to have more efficient TMS in fog computing.