Behavior Signature for Fine-grained Traffic Identification
Sung‐Ho Yoon, Jun‐Sang Park, Myung‐Sup Kim · 2015
With the rapid development of the Internet and a vigorous emergence of new applications, traffic identification has becom e a key issue for efficient network management. Although vario us methods have been proposed, there are still several limitations to achieving fine-grained and application-level traffic ident ification. In this paper, we propose a new signature model cal led a behavior signature for Internet traffic identification that utilizes the inter-flow relation of application traffic. The proposed behavior signature is a unique traffic behavior pattern appearing in the first few packets of plural traffic flows when a specific function is cond ucted by an application with a combination of various optional traffic features. This is in contrast to other existing signatur e models that usually focus on a singular packet or flow for feature extract ion and traffic identification. We proved the feasibility and applicability of the proposed behavior signature by developing an extraction and identification algorithm and by conducting experime nts on several popular applications.