Anomaly based Network Intrusion Detection using Machine Learning Techniques.
Anomaly based Network Intrusion Detection using Machine Learning Techniques.
复制标题
使用机器学习技术的基于异常的网络入侵检测。
DOI：
--
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
V. Gonjari
中科院分区：
文献类型：
--
作者：
Tushar Rakshe;V. Gonjari
— 在网络通信中，网络入侵是当今最受关注的问题。网络攻击事件的激增给网络服务带来了毁灭性的问题。人们已经开展了各种研究工作，以找到一种有效且高效的解决方案来防止网络入侵，以确保网络安全和隐私。机器学习是一种有效的分析工具，可以检测网络流量中发生的任何可疑事件。在本文中，我们开发了一种基于支持向量机和随机森林算法的分类器模型，用于网络入侵检测。 NSL-KDD 数据集是原始 KDDCUP’99 数据集的大幅改进版本，用于评估我们算法的性能。我们的检测算法的主要任务是根据描述每种网络流量模式的 41 个特征来对传入网络流量是正常还是攻击进行分类。使用SVM和随机算法实现了95%以上的检测准确率。比较两种算法的结果，可以看出随机森林算法比支持向量机更有效。
— In the network communications, network intrusion is the most important concern nowadays. The booming contingency of network attacks is a devastating problem for network services. Various research works are already conducted to find an effective and efficient solution to prevent intrusion in the network in order to ensure network security and privacy. Machine learning is an effective analysis tool to detect any suspicious events occurred in the network traffic flow. In this paper, we developed a classifier model based on SVM and Random Forest based algorithms for network intrusion detection. The NSL-KDD dataset, a much improved version of the original KDDCUP’99 dataset, was used to evaluate the performance of our algorithm. The main task of our detection algorithm was to classify whether the incoming network traffics are normal or an attack, based on 41 features describing every pattern of network traffic. The detection accuracy more than 95 % was achieved using SVM and Random algorithms. The results of two algorithms compared and it is observed that Random Forest algorithm is more effective than Support Vector Machine.