Machine Learning and Deep Learning based Intrusion Detection in Cloud Environment: A Review
A. Vinolia, N. Kanya, V. N. Rajavarman
Abstract
Due to its open and dispersed nature, cloud computing (CC) faces several security-related difficulties. As a result, it is weak and open to breaches that compromise the security, reliability, and integrity of cloud resources and provided services. The most widely utilized element of computer system security and compliance procedures that protects cloud environments from numerous threats and attacks is the intrusion detection system (IDS). The goal of this article is to study how deep learning (DL) and machine learning (ML) networks are used by various methodologies at various stages of the intrusion detection process to get improved outcomes. The goal of this work is to discuss the state of the art for detectingintrusions usingavariety of techniques, including soft computing, data mining, and other approaches. The experimental findings demonstrate that unsupervised, deep learning-based techniques achieve superior accuracy of 99.95%.