The Security and Privacy of Mobile Edge Computing: An Artificial Intelligence Perspective

TL;DR

This survey examines the security and privacy of Mobile Edge Computing (MEC) from an Artificial Intelligence perspective, anchored in the ETSI MEC reference architecture and enhanced with SDN/NFV considerations. It classifies AI techniques into supervised, unsupervised, semi supervised, and reinforcement learning, and maps them to layer based MEC security and privacy challenges, spanning IoT perception, network, and application layers, through MEC system/host levels. The work also surveys nonML AI approaches such as Bayesian networks and evolutionary algorithms, and provides a comprehensive review of AI enabled security and privacy solutions across IoT, MEC system, SDN, and NFV layers, highlighting opportunities, limitations, and future research directions. The paper aims to guide researchers and practitioners in deploying AI driven MEC security and privacy solutions and to identify practical challenges for real world 5G/6G MEC ecosystems.

Abstract

Mobile Edge Computing (MEC) is a new computing paradigm that enables cloud computing and information technology (IT) services to be delivered at the network's edge. By shifting the load of cloud computing to individual local servers, MEC helps meet the requirements of ultralow latency, localized data processing, and extends the potential of Internet of Things (IoT) for end-users. However, the crosscutting nature of MEC and the multidisciplinary components necessary for its deployment have presented additional security and privacy concerns. Fortunately, Artificial Intelligence (AI) algorithms can cope with excessively unpredictable and complex data, which offers a distinct advantage in dealing with sophisticated and developing adversaries in the security industry. Hence, in this paper we comprehensively provide a survey of security and privacy in MEC from the perspective of AI. On the one hand, we use European Telecommunications Standards Institute (ETSI) MEC reference architecture as our based framework while merging the Software Defined Network (SDN) and Network Function Virtualization (NFV) to better illustrate a serviceable platform of MEC. On the other hand, we focus on new security and privacy issues, as well as potential solutions from the viewpoints of AI. Finally, we comprehensively discuss the opportunities and challenges associated with applying AI to MEC security and privacy as possible future research directions.

Figures (3)

• Figure 1: Overall architecture of this paper.
• Figure 2: MEC reference architecture.
• Figure 3: Security and privacy threats of a typical MEC deployment.