An experimental analysis for malware detection using extrusions

Abstract

Today, the comprehensive protection of a computer network from malware is extremely important. The increasing usage of interactive internet applications in the areas of stock trades, medicine, weather forecasting, banks, businesses, education, defense, research etc. has induced a rise in risks and possibilities of misuse of computer networks. Over the last decade, malicious software or malware in the form of viruses, worms, Trojan horses, Botnets has risen to become a primary source of most of the threats used for scanning, distributed denial-of-service (DDoS) activities and direct attacks, taking place across the Internet. A number of solutions have been proposed in literature to defend against such threats from malware. Majority of these solutions uses the concept of inbound traffic approach for detection. The main goal of this paper is to work out a pragmatic solution to protect the network from the malware by exploring the feasibility of the concept of analysis of outbound traffic i.e Extrusion traffic only instead of intrusion traffic. Four different types of malware have been analyzed to check the validity of the proposed approach.