Using data analysis by deploying Artificial Neural Networks to increase honeypot security

The goal of this research is to increase honeypot security through data analysis with Artificial Neural Network (ANN). Thus, first we present an approach to detection presence of computer malcode in the honeypot based on ANN while using the computer's behavioral measures. Then, we identify significant features, which describe the activity of a malcode within a honeypot, by acquiring these from security experts. We suggest employing fisher's score, one of the feature selection techniques, for the dimensionality reduction and identification of the most prominent features to capture efficiently the computer behavior in content of malcode activity. Later on, we preprocess the dataset according to this technique and train the ANN model with preprocessed data. Finally, we evaluate the ability of the model to detect the presence of a malcode in the honeypot when honeypot is at risk.