Evaluation of CICIDS2017 with Qualitative Comparison of Machine Learning Algorithm
作者： Toka Elmasri , Nour Samir , Maggie Mashaly , Youmna Atef
DOI: 10.1109/IEEECLOUDSUMMIT48914.2020.00013
关键词:
摘要: Anomaly Intrusion Detection Systems (AIDS) are crucial for the network security of any organization due to evolution novel malware attacks that capable deceiving traditional detection methods. In this paper, we develop three AIDS models using machine learning K Nearest Neighbors (KNN), enhanced KNN and Local Outlier Factor (LOF) techniques. The approaches were applied on CICIDS2017 dataset training, testing evaluation. A comparison between was provided our model produced promising results with average accuracy 90.5% LOF approach. Contrary previous work, tested no prior training abnormal samples demonstrating an encouraging rate 92.74 % zero day attacks.
sci-hub.st 参考文章(10)
Levent Ertöz, Aleksandar Lazarevic, Vipin Kumar, Jaideep Srivastava, Aysel Ozgur, A Comparative Study of Anomaly Detection Schemes in Network Intrusion Detection. siam international conference on data mining. pp. 25- 36 ,(2003)
Yihua Liao, V.Rao Vemuri, Use of K-Nearest Neighbor classifier for intrusion detection11An earlier version of this paper is to appear in the Proceedings of the 11th USENIX Security Symposium, San Francisco, CA, August 2002 Computers & Security. ,vol. 21, pp. 439- 448 ,(2002) , 10.1016/S0167-4048(02)00514-X
Yang Li, Binxing Fang, Li Guo, You Chen, Network anomaly detection based on TCM-KNN algorithm Proceedings of the 2nd ACM symposium on Information, computer and communications security - ASIACCS '07. pp. 13- 19 ,(2007) , 10.1145/1229285.1229292
Dhanashri Ashok Bhosale, Vanita Manikrao Mane, Comparative study and analysis of network intrusion detection tools international conference on applied and theoretical computing and communication technology. pp. 312- 315 ,(2015) , 10.1109/ICATCCT.2015.7456901
Brightstarlang Wanswett, Hemanta Kumar Kalita, The Threat of Obfuscated Zero Day Polymorphic Malwares: An Analysis international conference on computational intelligence and communication networks. pp. 1188- 1193 ,(2015) , 10.1109/CICN.2015.230
Jianguo Jiang, Qian Yu, Min Yu, Gang Li, Jiuming Chen, Kunying Liu, Chao Liu, Weiqing Huang, None, ALDD: A Hybrid Traffic-User Behavior Detection Method for Application Layer DDoS trust security and privacy in computing and communications. pp. 1565- 1569 ,(2018) , 10.1109/TRUSTCOM/BIGDATASE.2018.00225
Doğukan Aksu, Serpil Üstebay, Muhammed Ali Aydin, Tülin Atmaca, Intrusion Detection with Comparative Analysis of Supervised Learning Techniques and Fisher Score Feature Selection Algorithm international symposium on computer and information sciences. pp. 141- 149 ,(2018) , 10.1007/978-3-030-00840-6_16
Imtiaz Ullah, Qusay H. Mahmoud, A Two-Level Hybrid Model for Anomalous Activity Detection in IoT Networks 2019 16th IEEE Annual Consumer Communications & Networking Conference (CCNC). pp. 1- 6 ,(2019) , 10.1109/CCNC.2019.8651782
Petros Toupas, Dimitra Chamou, Konstantinos M. Giannoutakis, Anastasios Drosou, Dimitrios Tzovaras, An Intrusion Detection System for Multi-class Classification Based on Deep Neural Networks 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA). pp. 1253- 1258 ,(2019) , 10.1109/ICMLA.2019.00206
F Richard Yu, Ying He, F Richard Yu, Ying He, Introduction to Machine Learning Deep Reinforcement Learning for Wireless Networks. pp. 1- 13 ,(2019) , 10.1007/978-3-030-10546-4_1