A Parallel Intrusion Detection System for High-Speed Networks

Abstract

The process speed of network-based intrusion detection systems (NIDSs) is still low compared with the speed of networks. As a result, few NIDS is applicable in a high-speed network. A parallel NIDS for high-speed networks is presented in this paper. By dividing the overall traffic into small slices, several sensors can analyze the traffic concurrently and significantly increase the process speed. For most attacks, our partition algorithm ensures that a single slice contains all the evidence necessary to detect a specific attack, making sensor-to-sensor interaction unnecessary. Meanwhile, by making use of the character of the network traffic, the algorithm can also dynamically balance all sensors’ loads. To keep the system as simple as possible, a specific sensor is used to detect the scan and the DoS attack. Although only one sensor is used for this kind of attacks, we argue that our system can still provide high process ability.

These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.