Improving Performance of Anomaly-Based IDS by Combining Multiple Classifiers
作者： Kazuya Kishimoto , Hirofumi Yamaki , Hiroki Takakura
关键词:
摘要: Intrusion detection systems (IDSs) play an important role to defend networks from cyber attacks. Among them, anomaly-based IDSs can detect unknown attacks like 0-day that are hard by using signature-based system. However, they have problems their performance depends on a learning dataset. It is very prepare appropriate dataset in static fashion, because the traffic Internet changes quite dynamically and complexity. In this paper, we propose method follows trend combining multiple classifiers. We evaluate our Kyoto2006+ existing algorithm.
sci-hub.se 参考文章(5)
Jungsuk Song, Hiroki Takakura, Yasuo Okabe, Yongjin Kwon, A Robust Feature Normalization Scheme and an Optimized Clustering Method for Anomaly-Based Intrusion Detection System Advances in Databases: Concepts, Systems and Applications. pp. 140- 151 ,(2007) , 10.1007/978-3-540-71703-4_14
J. SONG, K. OHIRA, H. TAKAKURA, Y. OKABE, Y. KWON, A Clustering Method for Improving Performance of Anomaly-Based Intrusion Detection System The IEICE transactions on information and systems. ,vol. 91, pp. 1282- 1291 ,(2008) , 10.1093/IETISY/E91-D.5.1282
R. Bellman, R. Kalaba, On adaptive control processes Ire Transactions on Automatic Control. ,vol. 4, pp. 1- 9 ,(1959) , 10.1109/TAC.1959.1104847
Jungsuk Song, Hiroki Takakura, Yasuo Okabe, Cooperation of Intelligent Honeypots to Detect Unknown Malicious Codes 2008 WOMBAT Workshop on Information Security Threats Data Collection and Sharing. pp. 31- 39 ,(2008) , 10.1109/WISTDCS.2008.10
J. B. Macqueen, Some methods for classification and analysis of multivariate observations Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, Volume 1: Statistics. ,vol. 1, pp. 281- 297 ,(1967)