Performance evaluation of Malicious traffic classification Using deep learning technique in Wireless networks

Abstract

Modern day Ransomwares are more sophisticated and the malware writers are evolving with new and advanced tools to evade the present security systems. Recently there was a huge impact in the business and financial loss due to the disruptive malware variant called Ransomware. The existing security mechanism available in the market are not up to the mark to defend against these attacks. Usually Ransomware is a malicious application, which needs a solid key derived from the external malicious server to initiate the encryption process. Restricting the communication to the external malicious server can prevent the hosts without any damage because the ransomware needs the unique key to proceed with the encryption. Traffic analysis plays the most important role in validating the performance and protection of the whole network traffic. Traffic analysis also plays a prime role in malware traffic detection. As the congestion of network traffic is increasing day by day, network traffic analysis need to be practiced periodically for ensuring and enhancing security. newlineMalicious traffic classification is the initial and primary step for any network-based security systems. These traffic classification systems include behavior-based anomaly detection system and Intrusion Detection System. The existing methods rely on the conventional techniques and process the data in the fixed sequence, which may lead to performance issues. Furthermore, conventional techniques require proper annotation to process the volumetric data. Relying on the data annotation for efficient traffic classification may leads to network loops and bandwidth issues within the network. newline newline