Hybrid Convolutional Multilayer Perceptron for Cyber Physical Systems (HCMP-CPS)

Abstract

Due to the rapid growth of cyber-security challenges via sophisticated attacks such as data injection attacks, replay attacks, etc., cyber-attack detection and avoidance system has become a significant area of research in Cyber-Physical Systems (CPSs). It is possible for different attacks to cause system failures, malfunctions. In the future, CPSs may require a cyber-defense system for improving its security. The different deep learning algorithms based on cyber-attack detection techniques have been considered for the detection and mitigation of different types of cyber-attacks. In this paper, the newly suggested deep learning algorithms for cyber-attack detection are studied and a hybrid deep learning model is proposed. The proposed Hybrid Convolutional Multilayer Perceptron for Cyber Physical Systems (HCMP-CPS) model is based on Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Multi-Layer Perceptron (MLP). The HCMP-CPS model helps to detect and classify attacks more accurately than the conventional models.