A Hybrid System Using Genetic Algorithm for Anomaly Intrusion Detection
Abstract: This paper proposes a new approach to design the system using a hybrid of misuse and anomaly detection for training of normal and attack packets respectively. The hybrid intrusion detection system combines the K-means and the genetic algorithm for anomaly detection. This algorithm operates on the KDD-99 Data set, this data set is used worldwide for evaluating the performance of different intrusion detection systems. The system can detect the intrusions and further classify them into four categories Denial of Service (DoS), U2R (User to Root), R2L (Remote to Local), and probe. The main goal is to reduce the false alarm rate of IDS.
Keywords: Clustering, Classification, K-Means, Genetic Algorithm, Detection rate, False alarm rate, Intrusion detection, data mining, KDD cup 99
How to Cite?: Arpitha J, Nagaraj Naik, "A Hybrid System Using Genetic Algorithm for Anomaly Intrusion Detection", Volume 4 Issue 4, April 2015, International Journal of Science and Research (IJSR), Pages: 3054-3057, https://www.ijsr.net/getabstract.php?paperid=SUB153890, DOI: https://dx.doi.org/10.21275/SUB153890