Automating Network Protocol Identification

摘要

The proliferation of computer network users has, in recent years, placed a strain on network resources, such as bandwidth and number allocations. This issue is more apparent where connectivity is limited, such as in developing countries. The provisioning of services over these congested resources needs to be managed, ensuring a fair quality of experience (QoE) to consumers and producers alike. Quality of service (QoS) techniques used to manage such resources require constant revision, catering for new application protocols introduced to the network on a daily basis. This research proposes an efficient, autonomous method for distinguishing application protocols through the use of a dynamic protocol classification system (DPCS). Using this method, the burden of signature creation is reduced, while the accuracy achieved in application protocol identification increases.