Predicting the Cyber Attackers; A Comparison of Different Classification Techniques

Identification of cybercriminals has been always a challenge for law enforcement agencies, they utilize different techniques and methods to tackle this issue. An effective predictor not only helps law enforcement agencies to chase the criminals but also is beneficial for cyber security experts to profile cyber attackers and their method of attacks and plan broad strategies for preventing future cyber threats. In this research we aim to investigate the effect of classification techniques on prediction of cyber attackers in past and possible future cyber-attacks. Our investigation is based on Open Source Intelligence and historical data about cyber-attacks. To train our proposed predictors, we use different classification algorithms and by comparing their accuracy in prediction of cyber attackers we will nominate the most accurate and reliable model. Finally to evaluate the predictor we apply a test set to discover to what extent a predictor can help law enforcement agencies in their investigations to chase cyber criminals.