Traffic feature-based botnet detection scheme emphasizing the importance of long patterns

Abstract

In this paper, we propose a traffic feature-based botnet detection scheme emphasizing the importance of long patterns. Since the communication sequences of bots are not easily changed, the long communication patterns of botnets are useful for detection. The proposed scheme emphasizes the long pattern’s importance by improving the feature extraction algorithms and giving weights to the long patterns with large occurrences. By the computer simulation with real dataset, we show the effectiveness of our scheme.