Reviewing a New Optimized an ANFIS-Based Framework for Detecting Intrusion Detection System with Machine Learning Algorithms (Deep Learning Algorithm)

Abstract

Today's world is becoming more interconnected due to the current global internet, communication, or ways of doing business that have recently shifted to cloud computing platforms in order to increase their speed and productivity. But such can also be affected by cyber attacks on cloud infrastructure services to be executed on various cloud platforms, increasing the number of attacks on such systems to neutralize any harm caused by a cyber attack on such cloud-based infrastructure. Although network administrators utilize intrusion detection systems (IDS) to detect threats and anomalies, they frequently only make available post-attack ready to act in cyber warfare. If we could predict risky behavior, network administrators or security-enhancing software could intervene before harm was done. Incoming intrusion detection messages should be viewed as a sequence. The fundamental function of an intrusion detection system (IDS) is to distinguish between regular and abnormal network traffic. As a result, robust intrusion detection systems (IDS) using deep learning model are required to find such cyber risk in form of threats and anomalies on cloud based infrastructure.