Machine Learning Techniques for Cybersecurity Detection: A Comparative Analysis
DOI:
https://doi.org/10.48047/Keywords:
Cybersecurity Detection, Machine Learning, Intrusion Detection Systems (IDS), Support Vector Machine (SVM), Random Forest, Convolutional Neural Networks (CNN), Artificial Neural Networks (ANN)Abstract
Advancements in computer and communication technologies have brought significant benefits to individuals, businesses, and governments. However, these technological improvements also pose challenges, particularly in terms of safeguarding sensitive information, securing data storage platforms, and ensuring data availability. Cyber terrorism has emerged as a critical issue in this context, with potential threats to public and national security from various groups, including criminal organizations, professionals, and cyber activists. To counter these threats, Intrusion Detection Systems (IDS) have been
developed to detect and prevent cyber attacks. This paper explores the application of machine learning algorithms, particularly Support Vector Machine (SVM), for detecting port scan attempts using the CICIDS2017 dataset. The SVM achieved an accuracy rate of 97.80%. Additionally, the study compares the performance of other algorithms, such as Random Forest, Convolutional Neural Networks (CNN), and Artificial Neural Networks (ANN), which achieved accuracies of 99.93%, 63.52%, and 99.11%,
respectively. These findings underscore the effectiveness of machine learning techniques in enhancing cybersecurity measures.
