Detecting Spam Zombies by Monitoring Outgoing Messages and DoS View

Abstract

Email Spam are major problem on internet. These Email Spam messages may contain code which is used to execute different malicious activities ranges from online searching of data, phishing, accessing lists, moving files, sharing channel information to DDoS attack against click fraud. Compromised machines are one of the key security threats on the internet; they are often used to launch various security attacks such as spamming and spreading malware, DDoS and identity theft. Finding machines which are used to send spam messages is very important to prevent these types of activities. These compromised machines in a network that are involved in the spamming activities, are known as spam zombies. In this paper we are going to present effective solution for detecting spam zombies by using SPOT algorithm. SPOT is designed based on a powerful statistical tool called Sequential Probability Ratio Test (SPRT), which has bounded false positive and false negative error rates. For comparison two more spam zombie detection algorithms are studied based on the number and the percentage of spam messages originated by the machine.