Automatic traffic signature extraction based on Smith-waterman algorithm for traffic classification

Nowadays, more and more applications use proprietary protocols, which make it difficult to identify them by using predefined well-known ports. Among all the mechanisms to identify and classify network traffic, the deep packet inspection (DPI)[1] is the most widely used method. In order to make the identification more accuracy, we should build a good set of application protocol signatures, however, it is a very time consuming task and demands a high expertise. This paper proposes an automatic traffic signature generation approach based on Smith-waterman algorithm, which is widely used for determining similar regions between two nucleotide or protein sequences. Our results show that it is a very accurate and quick approach compared to the approach that uses preceding application protocol analysis.