Intrusion Detection System Using Machine Learning Algorithms
INTERNATIONAL ENGINEERING AND TECHNOLOGY MANAGEMENT SUMMIT 2024, Ankara, Türkiye, 17 - 19 Ekim 2024, ss.116-121, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Basıldığı Şehir: Ankara
- Basıldığı Ülke: Türkiye
- Sayfa Sayıları: ss.116-121
- Ankara Üniversitesi Adresli: Hayır
Özet
With the exponential growth in computer network usage and the substantial increase in applications running on these networks, network security has become increasingly crucial. Systems inherently possess security vulnerabilities, which can lead to a higher frequency of attacks with potentially severe economic repercussions. Security vulnerabilities, especially in the defense industry, can cause significant damage not only to the economy but also to national security. Therefore, it is essential to accurately and promptly detect these vulnerabilities in network systems. This paper presents the development and training of an Intrusion Detection System (IDS) using a variety of classification techniques including Logistic Regression, k-Nearest Neighbors and Decision Trees. The primary objective is to accurately identify and differentiate between normal and malicious network packets in real-time, enhancing the overall security and resilience of network systems. A dataset consisting of 125972 data with 43 features was used in this study. Promising results were obtained when the decision tree algorithm was used on this data set.