AI-enabled Trust in Distributed Networks

Cybersecurity, as a crucial aspect of the information society, requires significant attention. Fortunately, the concept of trust, rooted in sociology, has been studied in order to enhance cybersecurity by evaluating the trustworthiness of nodes with artificial intelligence (AI) techniques in distributed networks (DNs). However, the scalability issues faced by AI-enabled trust hinder its integration with the DNs. Currently, there is a lack of a comprehensive review article that explores the current state of AI-enabled trust development applications. This paper aims to address this gap by providing a review of the state-of-the-art AI-enabled trust in DNs. This review focuses on the concept of trust and how it can be facilitated through AI, particularly utilizing machine learning and deep learning methods. Additionally, the paper provides a comprehensive comparison and analysis of three key domains in the field of AI-enabled trust: trust management (TM), intrusion detection systems (IDS), and recommender systems (RS). Some open problems and challenges that currently exist in the field are manifested, and some suggestions for future work are presented.