Malware traffic classification using principal component analysis and artificial neural network for extreme surveillance

Code-driven systems have extent to more than half of the world's populations in ambient data and connectivity, offering formerly unimagined opportunities and unexpected threats. Evolutions in Artificial Intelligence (AI) are seen increasing day by day especially in industrial builds. The unconventional technique of AI in cyber-attacks seems to be quite daunting. The idea of a machine growing its own knowledge through self-learning becomes sophisticated to attack things is a fretful problem to the cyber world. Most of the time, these AI enabled cyber-attacks are performed using advanced malwares which incorporates advanced evasion techniques to evade security perimeters. Traditional cyber security methods fail to cope with these attacks. In order to address these issues, robust traffic classification system using Principal Component Analysis (PCA) and Artificial Neural Network (ANN) is proposed for providing extreme surveillance. Further, these proposed method aims to expose various AI based cyber-attacks with their present-day impact, and their fortune in the future. Simulation is carried out using a self-developed autonomous agent which learns by itself. Experimental results confirm that the proposed schemes are efficient to classify the attack traffic with 99% of accuracy when compared to the state of the art methods.