MASiNet: Network Intrusion Detection for IoT Security Based on Meta-Learning Framework
- 17 May 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (14) , 25136-25146
Abstract
The rapid proliferation of Internet of Things (IoT) devices has led to an increased need for robust and efficient intrusion detection systems capable of identifying and mitigating novel threats. Traditional methods often struggle with the scarcity of labeled anomaly data, which is highly consequential, particularly in the context of IoT. In this study, we propose a novel few-shot learning (FSL) approach by leveraging a multistage attention Siamese network (MASiNet) for network traffic intrusion detection based on meta-learning framework. Unlike traditional methods, the proposed MASiNet model is capable of detecting intrusions with minimal labeled samples, addressing the challenge of scarce anomaly data. The model is trained using various attack samples and evaluates unknown samples by comparing similarities with a small set of known attack types. A well-structured cost function design, incorporating two specific losses, is introduced to optimize the effectiveness of the training process. Tested on the NSL_KDD and UNSW-NB15 data sets in a simulated FSL environment, the MASiNet model demonstrates superior performance in terms of accuracy, precision, and false alarm rate (FAR), outperforming existing methods. Furthermore, we have validated our approach through real-world evaluations. The proposed method provides an effective solution for intrusion detection in the context of FSL, offering a proficient solution that aligns with the dynamic nature of IoT networks.Keywords
Funding Information
- National Natural Science Foundation of China (62302454)
- Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies (2022B1212010005)
- Zhejiang Provincial Natural Science Foundation of China through a Major Program (LDQ24F020001)
- China Postdoctoral Science Foundation (2023M743403)
- National Science Foundation (62072408)
- Zhejiang Provincial Science Fund for Distinguished Young Scholars (LR24F020004)
- Scientific Research Project of National University of Defense Technology (22-ZZCX-07)
- Hefei Comprehensive National Science Center
- Jianghuai Advance Technology Center (00QK0021)
This publication has 20 references indexed in Scilit:
- Cross-Domain Industrial Intrusion Detection Deep Model Trained With Imbalanced DataIEEE Internet of Things Journal, 2022
- Emergent Deep Learning for Anomaly Detection in Internet of EverythingIEEE Internet of Things Journal, 2021
- Deep Learning for Network Traffic Monitoring and Analysis (NTMA): A SurveyComputer Communications, 2021
- Unknown Attack Detection Based on Zero-Shot LearningIEEE Access, 2020
- A Survey on Security and Privacy Issues in Edge-Computing-Assisted Internet of ThingsIEEE Internet of Things Journal, 2020
- CorrAUC: A Malicious Bot-IoT Traffic Detection Method in IoT Network Using Machine-Learning TechniquesIEEE Internet of Things Journal, 2020
- An Intrusion Detection Method Using Few-Shot LearningIEEE Access, 2020
- An Empirical Study of Spatial Attention Mechanisms in Deep Networks2019
- Squeeze-and-Excitation Networks2018
- Generalized Max Pooling2014