Sabri, FNMFNMSabriNorwawi, NMNMNorwawiSeman, KKSeman2024-05-292024-05-2920111738-7906WOS:000217333300014https://oarep.usim.edu.my/handle/123456789/12142Intrusion Detection Systems (IDS) are very important in determining how secure a system is, and to discover several types of attack such as Denial of Service (DOS), Probes and User to Root (U2R) attacks. However, recently false alarm rates and accuracy of detection are happens to be the most important issues and challenges in designing effective IDS. Therefore, this study is aimed at detecting denial of services attack and normal traffic using Knowledge Discovery and Data Mining Cup 99(KDD CUP 99) dataset to reduce the false alarm rates. Data mining is used to extract the useful information from large databases. The results have shown that the data mining technique reduces the false alarm rates and increase the accuracy of the system.en-USIntrusion detection systemaccuracyfalse alarm ratedata miningdenial of serviceArticle9599114