Comparative Approach for Intrusion Detection using CNN
Abstract
In computer network security, intrusion detection plays an important role in protecting systems from various threats. However, as intrusion techniques become more sophisticated, traditional detection methods have shown limitations in identifying new attacks. This research addresses the pressing issue of improving intrusion detection by utilizing Convolutional Neural Networks (CNN) algorithms, compared to various other machine learning techniques such as Support Vector Machines (SVM), K-Nearest Neighbors (KNN), Gaussian Naive Bayes (GNB), Decision Trees, and Gradient Boosting (GBoost). The main objective is to evaluate and compare the performance of these algorithms using a comprehensive dataset sourced from Kaggle, which includes 25,192 data and 42 features. Using metrics such as accuracy, precision, recall, and F1-score, the results show a complex pattern in the strengths and weaknesses of each. Surprisingly, CNN achieved exceptional accuracy, raising questions that require further investigation.
Downloads
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
IJICOM is an open-access journal. Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.