Treffer: Detection of cyber attacks using machine learning techniques.

The rapid growth of computer and communication technologies has enhanced connectivity and access to information but has also increased exposure to cyber threats, including digital terrorism. To address these risks, Intrusion Detection Systems (IDS) play a crucial role in monitoring and mitigating unauthorized network activities. This study focuses on detecting port scan attacks, a common reconnaissance technique used by attackers to identify vulnerabilities in target systems, which may lead to more severe breaches. Using the CICIDS2017 dataset, which includes both normal and malicious network traffic, we apply three supervised learning algorithms—Support Vector Machine (SVM), Decision Tree, and Random Forest—to classify port scan activities. The SVM model achieves an impressive precision rate of 97.80%, leveraging kernel functions to effectively handle high-dimensional, non-linear data. In comparison, the Decision Tree and Random Forest models demonstrate precision rates of 69.79%, indicating good performance, though less accurate than SVM. The IDS developed in this study is designed to provide early detection of cyber threats and alert security teams through email, SMS, and phone notifications. This multi-channel alert system ensures quick responses to emerging threats, minimizing potential damage. By integrating machine learning into IDS, this approach reduces human intervention, adapts to evolving attack patterns, and enhances the overall security posture of digital infrastructures, emphasizing the importance of next-generation machine learning technologies in cybersecurity. [ABSTRACT FROM AUTHOR]

Copyright of AIP Conference Proceedings is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)