FFT-RDNet: A Time–Frequency-Domain-Based Intrusion Detection Model for IoT Security

Resource-constrained Internet of Things (IoT) devices demand efficient and robust intrusion detection systems (IDSs) to counter evolving cyber threats. The traditional IDS models, however, struggle with high computational complexity and inadequate feature extraction, limiting their accuracy and gene...

Full description

Saved in:
Bibliographic Details
Main Authors: Bingjie Xiang, Renguang Zheng, Kunsan Zhang, Chaopeng Li, Jiachun Zheng
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/15/4584
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849406464367525888
author Bingjie Xiang
Renguang Zheng
Kunsan Zhang
Chaopeng Li
Jiachun Zheng
author_facet Bingjie Xiang
Renguang Zheng
Kunsan Zhang
Chaopeng Li
Jiachun Zheng
author_sort Bingjie Xiang
collection DOAJ
description Resource-constrained Internet of Things (IoT) devices demand efficient and robust intrusion detection systems (IDSs) to counter evolving cyber threats. The traditional IDS models, however, struggle with high computational complexity and inadequate feature extraction, limiting their accuracy and generalizability in IoT environments. To address this, we propose FFT-RDNet, a lightweight IDS framework leveraging depthwise separable convolution and frequency-domain feature fusion. An ADASYN-Tomek Links hybrid strategy first addresses class imbalances. The core innovation of FFT-RDNet lies in its novel two-dimensional spatial feature modeling approach, realized through a dedicated dual-path feature embedding module. One branch extracts discriminative statistical features in the time domain, while the other branch transforms the data into the frequency domain via Fast Fourier Transform (FFT) to capture the essential energy distribution characteristics. These time–frequency domain features are fused to construct a two-dimensional feature space, which is then processed by a streamlined residual network using depthwise separable convolution. This network effectively captures complex periodic attack patterns with minimal computational overhead. Comprehensive evaluation on the NSL-KDD and CIC-IDS2018 datasets shows that FFT-RDNet outperforms state-of-the-art neural network IDSs across accuracy, precision, recall, and F1 score (improvements: 0.22–1%). Crucially, it achieves superior accuracy with a significantly reduced computational complexity, demonstrating high efficiency for resource-constrained IoT security deployments.
format Article
id doaj-art-fb987efae13f4c668589ae622e7227cd
institution Kabale University
issn 1424-8220
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-fb987efae13f4c668589ae622e7227cd2025-08-20T03:36:22ZengMDPI AGSensors1424-82202025-07-012515458410.3390/s25154584FFT-RDNet: A Time–Frequency-Domain-Based Intrusion Detection Model for IoT SecurityBingjie Xiang0Renguang Zheng1Kunsan Zhang2Chaopeng Li3Jiachun Zheng4School of Ocean Informattion Engineering, Jimei University, Xiamen 361000, ChinaState Grid Fujian Electric Power Co., Ltd., Zhangzhou Power Supply Company, No. 13 Shengli East Road, Xiangcheng District, Zhangzhou 363000, ChinaState Grid Fujian Electric Power Co., Ltd., Zhangzhou Power Supply Company, No. 13 Shengli East Road, Xiangcheng District, Zhangzhou 363000, ChinaSchool of Ocean Informattion Engineering, Jimei University, Xiamen 361000, ChinaSchool of Ocean Informattion Engineering, Jimei University, Xiamen 361000, ChinaResource-constrained Internet of Things (IoT) devices demand efficient and robust intrusion detection systems (IDSs) to counter evolving cyber threats. The traditional IDS models, however, struggle with high computational complexity and inadequate feature extraction, limiting their accuracy and generalizability in IoT environments. To address this, we propose FFT-RDNet, a lightweight IDS framework leveraging depthwise separable convolution and frequency-domain feature fusion. An ADASYN-Tomek Links hybrid strategy first addresses class imbalances. The core innovation of FFT-RDNet lies in its novel two-dimensional spatial feature modeling approach, realized through a dedicated dual-path feature embedding module. One branch extracts discriminative statistical features in the time domain, while the other branch transforms the data into the frequency domain via Fast Fourier Transform (FFT) to capture the essential energy distribution characteristics. These time–frequency domain features are fused to construct a two-dimensional feature space, which is then processed by a streamlined residual network using depthwise separable convolution. This network effectively captures complex periodic attack patterns with minimal computational overhead. Comprehensive evaluation on the NSL-KDD and CIC-IDS2018 datasets shows that FFT-RDNet outperforms state-of-the-art neural network IDSs across accuracy, precision, recall, and F1 score (improvements: 0.22–1%). Crucially, it achieves superior accuracy with a significantly reduced computational complexity, demonstrating high efficiency for resource-constrained IoT security deployments.https://www.mdpi.com/1424-8220/25/15/4584internet of thingsFFTdepthwise separable convolutionresidual networkhybrid sampling
spellingShingle Bingjie Xiang
Renguang Zheng
Kunsan Zhang
Chaopeng Li
Jiachun Zheng
FFT-RDNet: A Time–Frequency-Domain-Based Intrusion Detection Model for IoT Security
Sensors
internet of things
FFT
depthwise separable convolution
residual network
hybrid sampling
title FFT-RDNet: A Time–Frequency-Domain-Based Intrusion Detection Model for IoT Security
title_full FFT-RDNet: A Time–Frequency-Domain-Based Intrusion Detection Model for IoT Security
title_fullStr FFT-RDNet: A Time–Frequency-Domain-Based Intrusion Detection Model for IoT Security
title_full_unstemmed FFT-RDNet: A Time–Frequency-Domain-Based Intrusion Detection Model for IoT Security
title_short FFT-RDNet: A Time–Frequency-Domain-Based Intrusion Detection Model for IoT Security
title_sort fft rdnet a time frequency domain based intrusion detection model for iot security
topic internet of things
FFT
depthwise separable convolution
residual network
hybrid sampling
url https://www.mdpi.com/1424-8220/25/15/4584
work_keys_str_mv AT bingjiexiang fftrdnetatimefrequencydomainbasedintrusiondetectionmodelforiotsecurity
AT renguangzheng fftrdnetatimefrequencydomainbasedintrusiondetectionmodelforiotsecurity
AT kunsanzhang fftrdnetatimefrequencydomainbasedintrusiondetectionmodelforiotsecurity
AT chaopengli fftrdnetatimefrequencydomainbasedintrusiondetectionmodelforiotsecurity
AT jiachunzheng fftrdnetatimefrequencydomainbasedintrusiondetectionmodelforiotsecurity