A Survey on Intrusion Detection Systems for IoT Networks Based on Long Short-Term Memory

The Internet of Things ( IoT) network is a promising technology that links both living and nonliving things in a worldwide fashion. Due to the wide availability and usage of connected devices in IoT networks, the number of attacks on these networks is continually increasing. Various types of cyber-security-enabled mechanisms have been developed to limit these attacks. Intrusion detection system (IDS) is among these mechanisms. IDS has two different functions: intrusion alarming, which represents the first function and detects malicious activity in the system, and the site security office (SSO), which represents the alarm and takes the appropriate action. Since sensitive data is more easily targeted and can be used immediately, the IDS works well while machine learning (ML) and especially deep learning (DL) algorithms are employed to identify and prevent various threats. Long Short-Term Memory (LSTM) is mainly utilized because it can forecast data held in long-term memory and provide more accurate predictions based on current information. In this paper, a comprehensive survey about using LSTM as a key solution for intrusion detection is provided, followed by a comparison of the most modern and extensive data sets used to detect intrusion attacks in the IoT environment.