Threats and attacks on computer systems network forensic analysis using machine learning techniques

With the advanced development of technology, there is an increase in the use of the internet and the number of devices connected to the network. With this increase, cyber attacks that cause significant losses for companies are increasing and these attacks appear in different ways. Network disconnection and loss of services provided by the network can cause serious losses for institutions. For this reason, it is important to develop defense strategies and take more effective measures against attacks. This thesis focuses on the analysis of attacks on information systems in terms of network forensics using machine learning techniques. First, different attack scenarios were carried out in the virtual environment. The data set was created by recording the network packets in the attacks and extracting the features. With this data set, classification was made using Random Forest, Support Vector Machine (SVM), Naive Bayes, Logistic Regression and Decision Tree classification algorithms and performance results were compared using performance metrics.