A Survey on Blockchain and Artificial Intelligence Technologies for Enhancing Security and Privacy in Smart Environments

【Author】 Oumaima, Fadi; Karim, Zkik; Abdellatif, El Ghazi; Mohammed, Boulmalf

【Source】IEEE ACCESS

【影响因子】3.476

【Abstract】Smart environments consist of a collection of sensors, actuators, and numerous computing units that improve human life. With the booming of smart environments, data generation has been notably increasing in recent years, which must be managed in a smart and optimal manner. The components (i.e., workstations and cloud) used for data processing are not the best to recommend since it is risky and resource costing. For that matter, enterprises, firms and companies are deploying blockchain technologies (BT) as a more suitable alternative. In fact, blockchain is a distributed transaction ledger ensuring the reliability and transparency of data. However, BT faces some inherent security challenges such as DoS, eclipse and double spending attacks as well as Advanced Persistent Threat (APT) and malware. Thus, advanced anomaly detection and mitigation approaches, especially the ones using artificial intelligence (AI) techniques (e. g. Machine Learning, Deep Learning, Federated Learning) are required to address the aforementioned issues. In combination, AI and BT are capable of detecting anomalies within blockchain networks with high accuracy. In this paper, with a focus on cyber security issues, we explore the challenges of blockchain deployment in smart environments. Additionally, we explore the use of anomaly detection AI-based techniques as a ledger of blockchain technologies to address the security issues in smart environments. Thus, we propose a framework that emphasizes the challenges of BT, values and capabilities of BT-AI integration. We also present research trends to highlight potential research paths for improving the security of blockchain networks using artificial intelligence.

【Keywords】Blockchain technology; artificial intelligence; security and privacy; smart environments; machine learning; anomaly detection

【发表时间】2022

【收录时间】2022-09-22

【文献类型】综述

【主题类别】

区块链治理-技术治理-区块链安全