Development of Intrusion Detection for Secure Social Internet of Things Based on Collaborative Edge Computing by Generative Adversarial Network using Hybrid Algorithms

Abstract

As cyber-attacks and cybercrime against cyber-physical systems (CPSs) increase, it is become harder to spot these intrusions. In the modern cyber environment, intrusion detection is one of the major security issues. A sizable number of methods that are based on machine learning strategies have been created. Thus, we have developed machine learning techniques for spotting the infiltration. When compared to conventional machine learning (ML) solutions, deep learning (DL) offers higher performance. When there is enough information, DL models nearly always produce great results. In contrast to other domains like NLP, image processing, software vulnerability, and many more, DL models have just recently been used to address the CPS cybersecurity issue.. Furthermore, it has been noted that a large number of DL models have been put out in recent papers to identify CPS cyber-attacks. The degree of complexity when superimposing cybersecurity on CPSs was attributed as a widely recognised explanation for why it is difficult to detect cyberattacks on CPSs. The UNSW-NB15 dataset was used in this system by referencing a repository of data. Finally, we must put the various categorization algorithms—including CNN, GAN, and logistic regression (LR)—into practise. The experimental findings demonstrate the correctness of the aforementioned algorithms.