A Review of Machine and Deep Learning Approaches for Enhancing Cybersecurity and Privacy in the Internet of Devices

Abstract

This review on deep learning (DL) and machine learning (ML) approaches for network analysis of intrusion detection was described in this study. Each ML/DL method is clearly outlined in the paper. The study identifies the datasets which function as primary tools for tracking network traffic and abnormality detection because the study found that data holds a dominant role in ML/DL methods. The study goes into more detail on the problems of using ML/DL in cybersecurity and suggests potential fixes and directions for further research. Applications and services for the Internet of Devices (IoD) are extensively used in fields including eHealth, smart industry, smart cities, and driverless cars. The Internet of electronic devices is therefore extensively networked and capable of sending sensitive and private data without the need for human contact. For this reason, protecting data privacy is vital. A deep review of current machine learning (ML) and deep learning (DL)-based privacy solutions for the Internet of Devices is presented in this study. In conclusion, we pinpoint a few feasible solutions for various risks and threats.