Review on Intrusion Detection in Edge Based IOT
Rajesh Singh, Anita Gehlot, Abhishek Joshi · 2022
A smart environment is essential in today's society. The term “smart environment” is used to describe an environment that is advanced in several ways. These may include technological advancements, improved infrastructure, improved modes of transportation, improved health care delivery, and other developments. With the help of the Internet of Things, smart environments may achieve their main objective of improving the quality of people's daily lives (IoT). In this context, “things” means any Internet-enabled device. IoT's total reliance on the Internet raises serious issues about security and privacy. Traditional methods of addressing security and privacy threats cannot be used with IoT devices because of their limited storage, processing capability, and dependence on external power sources. That's why it's crucial to develop a sophisticated IDS that can perform reliably in an IoT environment. Intruder detection systems (IDS) might be signature-based, anomaly-based, or hybrid. The delay introduced by IoT devices is particularly problematic for use in time-sensitive scenarios. To solve for this delay issue, edge computing was created. Machine learning is one approach that may be used to implement IDS. The purpose of this research is to learn everything that can be learned about various machine learning-based models for vulnerability scanning in edge-based Internet of Things (IoT) networks.