A network-based framework for RAT-bots detection

Remote access Trojans (RATs) are used by attackers to compromise and control the victim machine. In this work, a novel Network-based framework is introduced for detecting RAT bots based on data mining techniques. Several machine learning (ML) techniques are used to differentiate between benign and RAT infected machines. Various performance measurements are used to evaluate the performance of the proposed framework. Experimental results demonstrate that the proposed system can achieve accuracy of 97.2% with 3.8% false positive rate.