Abstract:
An 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 them for further research 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 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 systems is proposed: visual IDS (V-IDS). NSLKDD dataset, one of the large-scale datasets, is used. Data visualization techniques were applied in order to determine geometric relationships between records, and the data were classified by using the DL model. The model achieved 98% accuracy in total and even higher in some intrusion categories.
