ASNM: Advanced Security Network Metrics for Attack Vector Description

behavioral signature, detection, IDS, network metrics, security

The main goal of this paper was to present formal description of metrics extraction process with respect to a communication context. Then there was defined the set of metrics included in the final behavioral signature. Second part of the paper describes experiments performed with the state-of-the-art set of network metrics designed by A. Moore, which were compared to our proposed experimental set.

There is considerable interest in developing novel detection methods based on new metrics for description of network flow to identify connection characteristics, for instance to permit early identification of emerging security incidents, rapid detection of infections within internal networks, or instantaneous prevention of forming attacks. In this paper we propose a method for extraction data from network flow and contextual separation of partial connections using set of network metrics that create a signature defining the connection behavior. We begin with definition of input dataset of captured communication and the process of extraction metrics from separated connections. Then we define the set of metrics included in the final behavioral signature. Second part of the article describes experiments performed with the state-of-the-art set of network metrics with comparison to our proposed experimental set. The paper is concluded with the experiment results.