arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.07405cs.CRcs.LG
收藏

基于包装器决策树特征选择的网络入侵检测

Network Intrusion Detection Using Wrapper-based Decision Tree for Feature Selection

School of Computer Science and Technology, Changchun University of Science and Technology(长春理工大学计算机科学与技术学院)

Mubarak Albarka Umar, Chen Zhanfang, Yan Liu

摘要:

基于机器学习(ML)的入侵检测系统(IDS)面临的主要挑战之一是昂贵的计算复杂性,这在很大程度上是由于IDS数据集中包含冗余、不完整和不相关的特征。为了克服这一挑战,保证建立高效、准确的入侵检测模型,许多研究者在混合建模方法中使用了归一化和特征选择等预处理技术。在这项工作中,我们提出了一个混合IDS建模方法与算法的特征选择(FS)和另一个用于建立一个IDS。FS算法是一个基于包装器的决策树作为特征评估器。提出的FS方法与一些选定的ML算法结合使用,使用UNSW-NB 15数据集构建IDS模型。有些IDS模型是作为基线在一个单一的建模方法使用数据集的全部功能。我们评估我们提出的方法的有效性,通过比较它与基线模型,也与国家的最先进的作品。我们的方法实现了97.95%的最佳DR,并且与最先进的作品相比非常有效。因此,我们建议使用它,特别是在IDS建模与UNSW-NB 15数据集。

英文摘要:

One of the key challenges of machine learning (ML) based intrusion detection system (IDS) is the expensive computational complexity which is largely due to redundant, incomplete, and irrelevant features contain in the IDS datasets. To overcome such challenge and ensure building an efficient and more accurate IDS models, many researchers utilize preprocessing techniques such as normalization and feature selection in a hybrid modeling approach. In this work, we propose a hybrid IDS modeling approach with an algorithm for feature selection (FS) and another for building an IDS. The FS algorithm is a wrapper-based with a decision tree as the feature evaluator. The propose FS method is used in combination with some selected ML algorithms to build IDS models using the UNSW-NB15 dataset. Some IDS models are built as a baseline in a single modeling approach using the full features of the dataset. We evaluate the effectiveness of our propose method by comparing it with the baseline models and also with state-of-the-art works. Our method achieves the best DR of 97.95% and shown to be quite effective in comparison to state-of-the-art works. We, therefore, recommend its usage especially in IDS modeling with the UNSW-NB15 dataset.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑