Gnort: High Performance Network Intrusion Detection Using Graphics Processors

摘要: The constant increase in link speeds and number of threats poses challenges to network intrusion detection systems (NIDS), which must cope with higher traffic throughput perform even more complex per-packet processing. In this paper, we present an system based on the Snort open-source NIDS that exploits underutilized computational power modern graphics cards offload costly pattern matching operations from CPU, thus overall processing throughput. Our prototype system, called Gnort, achieved a maximum 2.3 Gbit/s using synthetic traces, while when monitoring real commodity Ethernet interface, it outperformed unmodified by factor two. results suggest can be used effectively speed up systems, as well other involve operations.