A Novel Traffic Analysis Model for Botnet Discovery in Dynamic Network

In this paper, we propose a collaborative pattern-based filtering algorithm which is a behavior-based approach to detect bots in association with case-based reasoning and fuzzy pattern recognition techniques. Network traces are used as a pivotal element to inspect bot-relevant domain names and IP addresses. Particularly, this method extracts the features, and making use of such features along with the IP address, the case-based reasoning is performed. If the address is known, it will be classified as a known bot, whereas if it is unknown, the fuzzy-based mapping is performed to detect botnet. This proposed approach especially reduces the search time and enhances the prediction accuracy up to 96%, and it is also observed that it improves the knowledge repository.