International Journal of Wireless and Microwave Technologies (IJWMT)
IJWMT Vol. 16, No. 3, 8 Jun. 2026
Cover page and Table of Contents: PDF (size: 1927KB)
Energy-Efficient and Privacy-Preserving Intrusion Detection in Edge-Based Networks Using Federated Self-Supervised Learning
PDF (1927KB), PP.254-276
Views: 0 Downloads: 0
Author(s)
Paras Kacha
1,*
Swati Shinde
1
Bal Virdee
2
Ashish Khanna
3
Index Terms
Intrusion Detection System (IDS), Edge Computing, Federated Learning, Self-Supervised Learning, Privacy- Preserving Security, Energy-Efficient IDS, Internet of Things (IoT), Autoencoder-Based Representation Learning, Model Pruning, Quantization, Resource-
Abstract
With the extensive adoption of edge computing and IoT infrastructure, the vulnerability landscape has expanded significantly along with stringent constraints concerning computation, energy efficiency, and data privacy. Traditional centralized IDS solutions tend to be less than ideal for such conditions, as they are highly dependent on centralized data labeling, large-scale computation, and constant traffic sharing. This paper presents FedSSL-IDS, a novel privacy-preserving IDS framework leveraging Federated Learning (FL) and Self-Supervised Learning (SSL), specifically designed for the needs of edge-based network architectures. The solution applies autoencoder-based self-supervised learning to extract informative latent feature representations of unlabeled network traffic, after which federated learning is performed on the lightweight classifier with supervised learning without any raw data sharing. In order to facilitate the implementation of the system on resource-limited edge devices, the system employs advanced model optimization methods, such as magnitude-based pruning and post-training quantization. Performance evaluations of the FedSSL-IDS framework were conducted using the CICIDS2017 dataset in a simulated federated edge environment with class-imbalanced and non-IID client distributions. According to the experimental results, the full precision model reached an average detection accuracy of 96.90% across all classes, whereas the major attack classes, like DDoS and PortScan, achieved impressive class-wise accuracy rates. Moreover, the combination of pruning and FP16 quantization greatly decreases the size of the model and computational cost during inference without compromising its near-native accuracy in detecting intrusions. Nevertheless, aggressive INT8 quantization leads to a substantial reduction in the detection performance of rare classes of attacks such as SQL injection attacks, showing that a compromise must be made between efficient compression and reliable detection in edge scenarios. Even though the presented framework increases the privacy level since there is no raw traffic exchange in federated training, sophisticated privacy-preserving techniques like differential privacy and secure aggregation are not part of the current design.
Cite This Paper
Paras Kacha, Swati Shinde, Bal Virdee, Ashish Khanna, "Energy-Efficient and Privacy-Preserving Intrusion Detection in Edge-Based Networks Using Federated Self-Supervised Learning", International Journal of Wireless and Microwave Technologies(IJWMT), Vol.16, No.3, pp. 254-276, 2026. DOI:10.5815/ijwmt.2026.03.17
Reference
[1]Khalid Alsubhi. A secured intrusion detection system for mobile edge computing. Applied Sciences, 14(4), 2024.
[2]Aitor Belenguer, Jose A Pascual, and Javier Navaridas. A review of federated learning applications in intrusion detection systems. Computer Networks, page 111023, 2025.
[3]Safa Ben Atitallah, Maha Driss, Wadii Boulila, and Anis Koubaa. Strengthening network intrusion detection in iot environments with self-supervised learning and few shot learning. In International Conference on Computational Collective Intelligence, pages 83–96. Springer, 2024.
[4]Razvan Beuran et al. Fedmse: Semi-supervised federated learning approach for iot network intrusion detection. Computers & Security, page 104337, 2025.
[5]Niccolo` Borgioli, Linh Thi Xuan Phan, Federico Aromolo, Alessandro Biondi, and Giorgio Buttazzo. Real-time packet-based intrusion detection on edge devices. In Proceedings of Cyber-Physical Systems and Internet of Things Week 2023, pages 234–240. 2023.
[6]Ping Deng and Yong Huang. Edge-featured multi-hop attention graph neural network for intrusion detection system. Computers & Security, 148:104132, 2025.
[7]Trong-Minh Hoang, Tuan-Anh Pham, Van-Viet Do, Van-Nhan Nguyen, and Manh-Hung Nguyen. A lightweight dnn-based ids for detecting iot cyberattacks in edge computing. In 2022 International Conference on Advanced Technologies for Communications (ATC), pages 136–140. IEEE, 2022.
[8]Shajjad Hossain, Sidi-Mohammed Senouci, Bouziane Brik, and Abdelwahab Boualouache. A privacy-preserving self-supervised learning-based intrusion detection system for 5g-v2x networks. Ad Hoc Networks, 166:103674, 2025.
[9]Danish Javeed, Muhammad Shahid Saeed, Muhammad Adil, Prabhat Kumar, and Alireza Jolfaei. A federated learning-based zero trust intrusion detection system for internet of things. Ad Hoc Networks, 162:103540, 2024.
[10]Zhigang Jin, Junyi Zhou, Bing Li, Xiaodong Wu, and Chenxu Duan. Fl-iids: A novel federated learning-based incremental intrusion detection system. Future Generation Computer Systems, 151:57–70, 2024.
[11]Amit Kumar, Vivek Kumar, and Abhay Pratap Singh Bhadauria. Optimizing intrusion detection in edge computing network: A hybrid ml approach with recursive feature elimination. International Journal of Intelligent Engineering & Systems, 18(1), 2025.
[12]Naila Latif, Wenping Ma, and Hafiz Bilal Ahmad. Advancements in securing federated learning with ids: a com- prehensive review of neural networks and feature engineering techniques for malicious client detection. Artificial Intelligence Review, 58(3):91, 2025.
[13]Pontus Lidholm, Tijana Markovic, Miguel Leon, and Per Erik Strandberg. Network intrusion detection using ma- chine learning on resource-constrained edge devices. In 2024 International Joint Conference on Neural Networks (IJCNN), pages 1–8, 2024.
[14]Nguyen Ngoc Minh, Pham Trung Hieu, Vu Hai, and Nguyen Huu Thanh. Dga-based intrusion detection system using federated learning method on edge devices. In 2024 International Conference on Information Networking (ICOIN), pages 509–514, 2024.
[15]Mohamad Moawad, Vong Wan Tze, Patrick Then Hang Hui, and Jason Yong Hsien Ming. Deep learning based intrusion detection for internet of things and edge devices. In 2023 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE), pages 01–06, 2023.
[16]Babatunde Olanrewaju-George and Bernardi Pranggono. Federated learning-based intrusion detection system for the internet of things using unsupervised and supervised deep learning models. Cyber Security and Applications, 3:100068, 2025.
[17]Pooja Potnurwar, Ayush Ainchwar, Rahul Neware, and Vrushali Bongirwar. Intrusion detection system for big data environment using deep learning. MDPI AG., 2024.
[18]Jahangir Shaikh, Yasir Awais Butt, and Hira Fatima Naqvi. Effective intrusion detection system using deep learning for ddos attacks. The Asian Bulletin of Big Data Management, 4(1):Science–4, 2024.
[19]Asis Kumar Tripathy, Alekha Kumar Mishra, and Rashmi Panda. Performance comparison and analysis of machine learning and deep learning models for network intrusion detection in iot-edge frameworks. In 2024 Second Inter- national Conference on Emerging Trends in Information Technology and Engineering (ICETITE), pages 1–6. IEEE, 2024.
[20]Renjie Xu, Guangwei Wu, Weiping Wang, Xing Gao, An He, and Zhengpeng Zhang. Applying self-supervised learn- ing to network intrusion detection for network flows with graph neural network. Computer Networks, 248:110495, 2024.