A Hybrid Network Model for Intrusion Detection Based on Session Patterns and Rate of False Errors

摘要

Nowadays, computer network systems play an increasingly important role in our society. They have become the target of a wide array of malicious attacks that can turn into actual intrusions. This is the reason why computer security has become an essential concern for network administrators. Intrusions can wreak havoc on LANs. And the time and cost to repair the damage can grow to extreme proportions. Instead of using passive measures to fix and patch security holes, it is more effective to adopt proactive measures against intrusions. Recently, several IDS have been proposed and they are based on various technologies. However, these techniques, which have been used in many systems, are useful only for detecting the existing patterns of intrusion. It can not detect new patterns of intrusion. Therefore, it is necessary to develop new technology of IDS that can find new pattern of intrusion. In this paper, we propose a hybrid network model for IDS based on reducing risk of false negative errors and false positive errors that can detect intrusion in the forms of the denial of service and probe attack detection method by measuring the resource capacities. The "IDS Evaluation Data Set" made by MIT was used for the performance evaluation.