A Network Intrusion Detection Algorithm Based on Rough Set Attribute-weighted Clustering

Intrusion detection system is automatic system which recognize intrusions to computers or computer network systems. Existing security detection system has many problems such as wrong detection of intrusions, missed intrusions, poor real-time performance. An intrusion detection algorithm is developed by combining a rough set algorithm with intrusion detection technology for security detection, attribute reduction, production of detection rules, and finally analysis of intrusion data with these rules. Based on it, a new rough set attribute-weighted clustering algorithm is used in network intrusion detection. Test rules show that the intrusion detection algorithm is more efficient than algorithm based on BP (back propagation) neural networks and vector machines, thereby, improving the detection ratio and reduces the wrong detection ratio. The system provides detection service effective for information system.