Comparative analysis on Intrusion Detection system through ML and DL Techniques: Survey

Abstract

Daily, large amounts of data are generated. Unauthorized users should be kept away from the data. Issues and problems arose one after the other as a result of the continuous development of network security. To avoid these malicious attacks, deep learning and machine learning methodologies are frequently used. Machine learning is a branch of the computer field that studies computational algorithms to convert empirical data into usable models. This field originated from the communities of traditional statics and intelligent retrieval. Machine learning includes deep learning as a subset. A system that can be trained to recognise objects using raw input has referred to as a deep learning system. In this study, we are applying DL techniques such as CNN, DNN, LSTM and RNN on NSL-KDD dataset. In this paper, we conduct a comparative analysis of multiple algorithms to determine which model is best for network security based on the network conditions and environment.