Security and privacy of industrial big data: Motivation, opportunities, and challenges

Abstract

With the rapid growth of the Industrial Internet of Things (IIoT), an abundance of data is generated, and various data acquisition, analytics, and storage mechanisms are developed intelligently for smart industrial productions. Big heterogeneous data of IIoT suffers from security and privacy issues, which are the main hurdles for smooth industrial operations and pose a serious concern to the widespread adoption of IIoT. The existing studies suffer from security loopholes and privacy-preserved solutions for industrial data in a distributed environment. However, emerging technologies like Blockchain, Federated Learning (FL), and Sixth Generation (6G) are potential candidates to provide reliability, security, and privacy in IIoT networks. The blockchain offers the temper proof of security due to its distributive absolute nature. The FL does not share data with the centralized system for training purposes, which ensures data privacy. Finally, 6G communication is used for faster data acquisition and low latency in the mobility-based distributed nature of industrial big data.

In this survey, we present an in-depth analysis of these emerging technologies in IIoT, their motivations, various IIoT applications, current challenges, and future directions regarding industrial big data security and privacy. In addition, an exhaustive investigation of privacy and security threats in industrial big data (acquisition, analytics, and storage) is considered. To this end, various industrial applications, software tools for big data, blockchain, FL, and 6G, as well as a proof of concept for anomaly detection on time-series data, are provided in detail. Lastly, this study aims to provide research challenges and future directions in industrial applications to achieve big data security and privacy.