Detecting Port Scan Attempts with Comparative Analysis of Deep Learning and Support Vector Machine Algorithms

Abstract

Compared to the past, developments in computer and communication technologies have provided extensive and advanced changes. The usage of new technologies provide great benefits to individuals, companies, and governments, however, it causes some problems against them. For example, the privacy of important information, security of stored data platforms, availability of knowledge etc. Depending on these problems, cyber terrorism is one of the most important issues in todays world. Cyber terror, which caused a lot of problems to individuals and institutions, has reached a level that could threaten public and country security by various groups such as criminal organizations, professional persons and cyber activists. Thus, Intrusion Detection Systems (IDS) have been developed to avoid cyber attacks. In this study, deep learning and support vector machine (SVM) algorithms were used to detect port scan attempts based on the new CICIDS2017 dataset and 97.80%, 69.79% accuracy rates were achieved respectively.