Detection Model for Cyber Attacks-Application of Data Mining

Intrusion detection systems (IDS) are important elements in network defenses to help protect against increasingly sophisticated cyber attacks. This project objective presents a novel anomaly detection technique that can be used to detect previously unknown attacks on a network by identifying attack features. This effects-based feature identification method uniquely combines k-means clustering; NaiveBayes feature selection and C4.5 decision tree classification for finding cyber attacks with a high degree of accuracy and it used KDD99CUP dataset as input. Basically it detects whether the attacks are there or not like IPSWEEP NEPTUNE SMURF.