arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.12722cs.NIcs.CRcs.LG
收藏

基于机器学习的物联网网络入侵检测中的特征提取

Feature Extraction for Machine Learning-based Intrusion Detection in IoT Networks

University of Queensland(昆士兰大学);University of New South Wales(新南威尔士大学)

Mohanad Sarhan, Siamak Layeghy, Nour Moustafa, Marcus Gallagher, Marius Portmann

AI总结:

本文探究物联网入侵检测中特征提取与机器学习模型的泛化性,发现无单一方法适用于所有数据集,并提出需通用基准特征集以促进研究。

摘要:

大量物联网网络中的安全漏洞已证明当前网络入侵检测系统(NIDS)的不可靠性。因此,网络中断和敏感数据丢失事件频发,这促使了改进NIDS技术的活跃研究领域。在对相关工作的分析中,观察到大多数研究者旨在通过在NIDS数据集上使用一组未经尝试的特征缩减(FR)和机器学习(ML)技术组合来获得更好的分类结果。然而,这些数据集在特征集、攻击类型和网络设计方面各不相同。因此,本文旨在探究这些技术能否在不同数据集之间进行泛化。使用了六种ML模型:深度前馈网络(DFF)、卷积神经网络(CNN)、循环神经网络(RNN)、决策树(DT)、逻辑回归(LR)和朴素贝叶斯(NB)。使用三个基准数据集:UNSW-NB15、ToN-IoT和CSE-CIC-IDS2018,评估了三种特征提取(FE)算法——主成分分析(PCA)、自编码器(AE)和线性判别分析(LDA)的准确性。尽管PCA和AE算法已被广泛使用,但对其最优提取维度的确定却被忽视。结果表明,没有任何一种明确的FE方法或ML模型能在所有数据集上取得最佳分数。为每个数据集确定了最优提取维度,且LDA在两个数据集上降低了ML模型的性能。使用方差来分析LDA和PCA的提取维度。最后,本文得出结论:数据集的选择显著改变了所应用技术的性能。我们认为,需要一个通用的(基准)特征集来促进该领域研究的进一步发展和进步。

英文摘要:

A large number of network security breaches in IoT networks have demonstrated the unreliability of current Network Intrusion Detection Systems (NIDSs). Consequently, network interruptions and loss of sensitive data have occurred, which led to an active research area for improving NIDS technologies. In an analysis of related works, it was observed that most researchers aim to obtain better classification results by using a set of untried combinations of Feature Reduction (FR) and Machine Learning (ML) techniques on NIDS datasets. However, these datasets are different in feature sets, attack types, and network design. Therefore, this paper aims to discover whether these techniques can be generalised across various datasets. Six ML models are utilised: a Deep Feed Forward (DFF), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Decision Tree (DT), Logistic Regression (LR), and Naive Bayes (NB). The accuracy of three Feature Extraction (FE) algorithms; Principal Component Analysis (PCA), Auto-encoder (AE), and Linear Discriminant Analysis (LDA), are evaluated using three benchmark datasets: UNSW-NB15, ToN-IoT and CSE-CIC-IDS2018. Although PCA and AE algorithms have been widely used, the determination of their optimal number of extracted dimensions has been overlooked. The results indicate that no clear FE method or ML model can achieve the best scores for all datasets. The optimal number of extracted dimensions has been identified for each dataset, and LDA degrades the performance of the ML models on two datasets. The variance is used to analyse the extracted dimensions of LDA and PCA. Finally, this paper concludes that the choice of datasets significantly alters the performance of the applied techniques. We believe that a universal (benchmark) feature set is needed to facilitate further advancement and progress of research in this field.

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。

↑