|
Frontiers of Information Technology & Electronic Engineering
ISSN 2095-9184 (print), ISSN 2095-9230 (online)
2025 Vol.26 No.6 P.862-876
A subspace-based few-shot intrusion detection system for the Internet of Things
Abstract: Deep learning-based intrusion detection systems rely on numerous training samples to achieve satisfactory detection rates. However, in the real-world Internet of Things (IoT) environments, the diversity of IoT devices and the subsequent fragmentation of attack types result in a limited number of training samples, which urgently requires researchers to develop few-shot intrusion detection systems. In this study, we propose a subspace-based approach for few-shot IoT intrusion detection systems to cope with the dilemma of insufficient learnable samples. The method is based on the principle of classifying metrics to identify network traffic. After feature extraction of samples, a subspace is constructed for each category. Next, the distance between the query samples and the subspace is calculated by the metric module, thus detecting malicious samples. Subsequently, based on the CICIoT2023 dataset we construct a few-shot IoT intrusion detection dataset and evaluate the proposed method. For the detection of unknown categories, the detection accuracy is 93.52% in the 5-way 1-shot setting, 92.99% in the 5-way 5-shot setting, and 93.65% in the 5-way 10-shot setting.
Key words: Intrusion detection system; Few-shot learning; Internet of Things; Subspace
1浙江理工大学信息科学与工程学院,中国杭州市,310027
2嘉兴大学信息科学与工程学院,中国嘉兴市,314000
摘要:基于深度学习的入侵检测系统依赖大量的训练样本才能达到令人满意的检测率。然而,在实际的物联网环境中,物联网设备种类多,攻击类型碎片化,导致训练样本数较小,这迫切需要研究者们开发小样本入侵检测系统。为此,本文提出基于子空间的小样本物联网入侵检测系统方法,来应对可学习样本不足的困境。该方法基于度量分类的思想来识别网络流量,对样本进行特征提取后,为每一个类别构造一个子空间,然后通过度量模块计算查询样本与子空间的距离,从而实现对恶意样本的检测。基于CICIoT2023数据集,构建了小样本物联网入侵检测数据集,并对所提方法进行评估。对于未知类别的检测,在5-way 1-shot(5类,每类仅1个标注样本)设置下检测准确率为93.52%,在5-way 5-shot设置下检测准确率为92.99%,在5-way 10-shot设置下检测准确率为93.65%。
关键词组:
References:
Open peer comments: Debate/Discuss/Question/Opinion
<1>
DOI:
10.1631/FITEE.2400556
CLC number:
TP393
Download Full Text:
Downloaded:
1206
Download summary:
<Click Here>Downloaded:
290Clicked:
675
Cited:
0
On-line Access:
2025-07-02
Received:
2024-07-02
Revision Accepted:
2025-07-02
Crosschecked:
2024-12-09