Embedded Wireless Context-Aware Intrusion Detection for Edge Networks: An Adaptive Architecture
DOI:
https://doi.org/10.70112/ajcst-2026.15.1.4415Keywords:
Anomaly Detection, Behavioral Analysis, Context-Aware Security, Edge Computing, Internet of Things , Intrusion Detection System Temporal , Feature EngineeringAbstract
The growth of Internet of Things (IoT) deployments has intensified security challenges in resource-constrained edge environments. This study presents an Embedded Wireless Context-Aware Intrusion Detection System (EWCA-IDS) that integrates contextual feature engineering with a fused ensemble learning framework to enhance intrusion detection reliability. The proposed architecture embeds temporal encodings, cumulative behavioral features, and contextual interactions into the detection pipeline and employs an optimized XGBoost-based fused engine to generate a unified anomaly confidence score. Experimental results using the TON_IoT dataset demonstrate strong detection performance, achieving an overall accuracy of 0.98, an ROC–AUC of 0.9975, and a high attack recall of 0.99, indicating effective detection of malicious activity with low false-negative rates. The distributional and temporal analyses demonstrate clear class separability and stable anomaly score behavior, while feature importance and correlation results indicate the influence of contextual and aggregated features. These findings support the robustness, interpretability, and suitability of the proposed intrusion detection framework beyond conventional metric-centric approaches. Further studies will focus on integrating adaptive, lightweight online learning to address evolving attack patterns in real-time edge deployments.
References
[1] U. Rehman et al., “Internet of Things in healthcare research: Trends, innovations, security considerations, challenges and future strategy,” Int. J. Intell. Syst., vol. 2025, no. 1, Jan. 2025, doi: 10.1155/int/8546245.
[2] M. Mansour et al., “Internet of Things: A comprehensive overview on protocols, architectures, technologies, simulation tools, and future directions,” Energies, vol. 16, no. 8, p. 3465, Apr. 2023, doi: 10.3390/en16083465.
[3] H. N. S. Aldin, M. R. Ghods, F. Nayebipour, and M. N. Torshiz, “A comprehensive review of energy harvesting and routing strategies for IoT sensors sustainability and communication technology,” Sensors Int., vol. 5, p. 100258, 2024, doi: 10.1016/j.sintl.2023.100258.
[4] A. I. Zreikat, Z. AlArnaout, A. Abadleh, E. Elbasi, and N. Mostafa, “The integration of the Internet of Things (IoT) applications into 5G networks: A review and analysis,” Computers, vol. 14, no. 7, p. 250, Jun. 2025, doi: 10.3390/computers14070250.
[5] T. Sasi, A. H. Lashkari, R. Lu, P. Xiong, and S. Iqbal, “A comprehensive survey on IoT attacks: Taxonomy, detection mechanisms and challenges,” J. Inf. Intell., vol. 2, no. 6, pp. 455–513, Nov. 2024, doi: 10.1016/j.jiixd.2023.12.001.
[6] G. Akwaronwu, I. U. Akwaronwu, and O. J. Adeniyi, “Machine learning for detecting DoS attack: A comparative approach,” Br. J. Comput. Netw. Inf. Technol., vol. 8, no. 2, pp. 51–70, 2025, doi: 10.52589/bjcnit-i0v0hk0y.
[7] B. G. Akwaronwu, I. U. Akwaronwu, and O. J. Adeniyi, “Brute Force Attack Detection in Network Traffic Using Convolutional Neural Networks,” Asian J. Res. Comput. Sci., vol. 18, no. 5, pp. 387–402, Apr. 2025, doi: 10.9734/ajrcos/2025/v18i5662.
[8] A. A. Al-Saedi, V. Boeva, E. Casalicchio, and P. Exner, “Context-aware edge-based AI models for wireless sensor networks—An overview,” Sensors, vol. 22, no. 15, pp. 1–33, 2022, doi: 10.3390/s22155544.
[9] L. Li, Q. Zhang, X. Xiong, A. Li, and G. Chen, “A fault diagnosis and prediction method for wireless sensor networks based on attention mechanism fused neural networks,” Int. J. Commun. Syst., vol. 38, no. 15, Oct. 2025, doi: 10.1002/dac.70244.
[10] A. Bahadori-Jahromi, S. Room, C. Paknahad, M. Altekreeti, Z. Tariq, and H. Tahayori, “The role of artificial intelligence and machine learning in advancing civil engineering: A comprehensive review,” Appl. Sci., vol. 15, no. 19, p. 10499, Sep. 2025, doi: 10.3390/app151910499.
[11] H. G. A. Umar et al., “Energy-efficient deep learning-based intrusion detection system for edge computing: A novel DNN-KDQ model,” J. Cloud Comput., vol. 14, no. 1, p. 32, 2025, doi: 10.1186/s13677-025-00762-9.
[12] Y. Huang, M. Ma, W. J. K. Raymond, and C.-O. Chow, “An adaptive intrusion detection system for the Internet of Things using large language models and post-quantum-secure blockchain,” Comput. Netw., p. 111819, Nov. 2025, doi: 10.1016/j.comnet.2025.111819.
[13] F. Alserhani, “Intrusion detection and real-time adaptive security in medical IoT using a cyber-physical system design,” Sensors, vol. 25, no. 15, p. 4720, Jul. 2025, doi: 10.3390/s25154720.
[14] M. N. Halgamuge and D. Niyato, “Adaptive edge security framework for dynamic IoT security policies in diverse environments,” Comput. Secur., vol. 148, p. 104128, Jan. 2025, doi: 10.1016/j.cose.2024.104128.
[15] Z. Noor, S. Hina, F. Hayat, and G. A. Shah, “An intelligent context-aware threat detection and response model for smart cyber-physical systems,” Internet Things, vol. 23, 2023, doi: 10.1016/j.iot.2023.100843.
[16] J. Violos, G. Mamanis, I. Kompatsiaris, and S. Papadopoulos, “Cognition and context-aware decision-making systems for a sustainable planet: A survey on recent advancements, applications and open challenges,” Discov. Sustain., vol. 6, no. 1, p. 235, 2025, doi: 10.1007/s43621-025-00954-y.
[17] N. Mazhar, R. Salleh, M. A. Hossain, and M. Zeeshan, “SDN-based intrusion detection and prevention systems using manufacturer usage description: A survey,” Int. J. Adv. Comput. Sci. Appl., vol. 11, no. 12, pp. 717–737, 2020, doi: 10.14569/IJACSA.2020.0111283.
[18] A. Hozouri, A. Mirzaei, and M. Effatparvar, “A comprehensive survey on intrusion detection systems with advances in machine learning, deep learning and emerging cybersecurity challenges,” Discov. Artif. Intell., vol. 5, no. 1, p. 314, 2025, doi: 10.1007/s44163-025-00578-1.
[19] J. O. Adeyemi, S. O. Ogunlere, and B. G. Akwaronwu, “Real-Time Detection of Examination Malpractices Using Convolutional Neural Networks and Video Surveillance: A Systematic Review with Meta-Analysis,” Br. J. Comput. Netw. Inf. Technol., vol. 8, no. 2, pp. 15–50, May 2025, doi: 10.52589/BJCNIT-QC5EELJE.
[20] E. C. Nkoro, J. N. Njoku, C. I. Nwakanma, J. M. Lee, and D.-S. Kim, “MetaWatch: Trends, challenges, and future of network intrusion detection in the metaverse,” IEEE Internet Things J., vol. 12, no. 16, pp. 32469–32492, Aug. 2025, doi: 10.1109/JIOT.2025.3568477.
[21] U. Khan, F. M. Khan, Z. A. Haider, and F. Alturise, “Integrating AI, blockchain, and edge computing for zero-trust IoT security: A comprehensive review of advanced cybersecurity framework,” Comput. Mater. Contin., vol. 85, no. 3, pp. 4307–4344, 2025, doi: 10.32604/cmc.2025.070189.
[22] Singh et al., “A systematic review of blockchain, AI, and cloud integration for secure digital ecosystems,” Int. J. Networked Distrib. Comput., vol. 13, no. 2, p. 28, 2025, doi: 10.1007/s44227-025-00072-1.
[23] N. Moustafa, “The TON_IoT datasets,” UNSW Canberra at ADFA, Canberra, Australia, 2021. [Online]. Available: https://research.unsw.edu.au/projects/toniot-datasets.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Centre for Research and Innovation
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
