A novel approach for intrusion detection systems: V-IDS

Abstract

Intrusion Detection System (IDS) is a security mechanism that detects abnormal activities in a network. An ideal IDS must detect intrusion attempts and maybe categorize for further researches and keep false positive analysis at a very low level. IDSs are used in the analysis of network traffic data at all sizes. Studies on this subject focused on machine learning (ML) techniques, even though the performance rates are high, it is seen that processes such as data understanding, preprocessing and consistency tests are time consuming and laborious. For this reason, the use of deep learning (DL) models that automatically perform the mentioned steps has become very popular. In this study, a high-performance approach that can be applied in real time system is proposed which is named V-IDS (Visual IDS). NSL-KDD data set which is one of the large-scale datasets, is used. Data visualization (DV) techniques were applied in order to determine geometric relationships between records and the data were classified by using DL model. The model achieved 98 percentage accuracy in total and even higher in some intrusion categories.