Performance Evaluation of Intrusion Detection System Using Anomaly and Signature Based Algorithms to Reduction False Alarm Rate and Detect Unknown Attacks

With the rapidly growth of technology, used Internet become an important part in human life it used in many sectors of society, communicating over global network, sending or receiving sensitive data is risk because different techniques are used by attackers to intercept and exposed data. As a result, strong security technique is required to guaranteeing the user data. Many methods proposed to improve security issues. Intrusion detection system (IDS) is used to observe unwanted action on network systems and individual computers. However due to opposite effect of using IDS, using individual methods of IDS only misuse or anomaly attacks can be detected. This paper proposed a model that integrates both approaches signature and anomaly based of IDS to reduce obtained alerts and detects new attacks. False alarm rate, accuracy, and detect attacks are the parameters used to evaluate effectiveness of hybrid IDS in addition Knowledge Discovery Data Mining (KDD) CUP 99 dataset and Waikato Environment for Knowledge Analysis (WEKA) program has been used for testing the proposed hybrid IDS.