Adaptive Spatio-Temporal Deep Learning for Robust Cyber Threat Detection Across IoT Environments
DOI:
https://doi.org/10.4108/eetiot.10791Keywords:
Real-time Intrusion detection, Convolutional Neural Networks, Temporal Convolutional Networks, Synthetic Minority Oversampling Technique, Industrial control systems, Internet of ThingsAbstract
In interconnected systems such as the Internet of Things (IoT), industrial control systems, and smart cities, real-time intrusion detection is crucial in smart network environments. It analyses network traffic in real time, enabling rapid detection and mitigation of cyber threats. With the help of artificial intelligence, including deep learning, real-time intrusion detection systems (IDS) can spot suspicious patterns, adapt to new-fangled attack vectors, and keep latency low, all without sacrificing system performance or reliability. This paper addresses intrusion detection in smart network environments by introducing Net Sentry DL, a deep learning framework. To extract spatio-temporal features and improve interpretability, the model uses a combination of CNNs, TCNs, and attention-guided fusion. Data imbalance and noise are addressed using an entropy-based pre-processing method and a class-preserving algorithm called Synthetic Minority Oversampling Technique (SMOTE). The UNSW-NB15, BoT-IoT, and TON_IoT benchmark datasets are used to assess Net Sentry DL. It surpasses models such as SVM, Random Forest, LSTM, GRU, and CNN in binary classification, reaching up to 0.99 accuracy and 0.98 F1-score on BoT-IoT. With TON_IoT, it achieves an accuracy of 0.95, and with BoT-IoT, up to 0.97, in multi-class configurations. Using SHAP, attention heatmaps, and gated fusion visualisations, the model exhibits strong explainability and robust generalisation, as demonstrated by cross-dataset testing. Through ONNX conversion and low quantisation loss (0.7%), it efficiently deploys and achieves low inference time (37ms/sample). The significance of each module, particularly CP-SMOTE and the TCN-attention combination, has been confirmed by ablation studies. For ever-changing IoT-based infrastructures, Net Sentry DL demonstrates competitive accuracy, interpretability, and deployment efficiency for intrusion detection.
Downloads
References
[1] Varaprasad R, Veeresha M. A comprehensive analysis of intrusion detection system using machine learning and deep learning algorithms. In: 2024 International Conference on Intelligent Algorithms for Computational Intelligence Systems (IACIS); 2024 Aug; 12: 1–5. IEEE.
[2] Almeida L, Rodrigues P, Teixeira R, Antunes M, Aguiar RL. Privacy-preserving defense: Intrusion detection in IoT using federated learning. In: 2024 IEEE 22nd Mediterranean Electrotechnical Conference (MELECON); 2024 Jun; 908–913. IEEE.
[3] Venkatasubramanian S, Ch SPK, Babu BP. Overcoming dataset imbalances and computational challenges in IoT intrusion detection: A SMOTE-enhanced transformer-based model. In: 2025 IEEE 14th International Conference on Communication Systems and Network Technologies (CSNT); 2025 Mar; 1195–1204. IEEE.
[4] Singh NJ, Hoque N, Singh KR, Bhattacharyya DK. Botnet-based IoT network traffic analysis using deep learning. Security and Privacy. 2024; 7(2): e355.
[5] Tazeen S. Deep learning-driven attack detection in IoT networks: A comprehensive study. In: Proceedings of Fourth International Conference on Computing and Communication Networks (ICCCN 2024); 2025; 1294:39. Springer.
[6] Krishnan D, Shrinath P. Robust botnet detection approach for known and unknown attacks in IoT networks using stacked multi-classifier and adaptive thresholding. Arabian Journal for Science and Engineering. 2024;49(9):12561–12577.
[7] Tyagi K, Ahlawat A, Chaudhary H. IoT network security: NetFlow traffic analysis and attack classification using machine learning techniques. In: 2024 11th International Conference on Reliability, Infocom Technologies and Optimization (ICRITO); 2024 Mar; 1–8. IEEE.
[8] Srinivasan V, Raj VH, Thirumalraj A, Nagarathinam K. Detection of data imbalance in MANET network based on ADSY-AEAMBi-LSTM with DBO feature selection. Journal of Autonomous Intelligence. 2024;7(4):1094.
[9] Islam MS, Yusuf A, Gambo MD, Barnawi AY. A novel few-shot ML approach for intrusion detection in IoT. Arabian Journal for Science and Engineering. 2024;1–15.
[10] Imtiaz N, Wahid A, Abideen SZU, Kamal MM, Sehito N, Khan S, et al. A deep learning-based approach for detection of IoT intrusion attacks through optical networks. Photonics. 2025;12(35):1–39.
[11] Dharshiniya S. IoT network intrusion detection with deep learning and voice alerts. In: 2024 International Conference on IoT Based Control Networks and Intelligent Systems (ICICNIS); 2024 Dec; 354–360. IEEE.
[12] Anusuya VS, Baswaraju S, Thirumalraj A, Nedumaran A. Securing MANET by detecting intrusions using CSO and XGBoost model. In: Intelligent Systems and Industrial Internet of Things for Sustainable Development; 2024; 219–234. CRC Press.
[13] Bhuiyan MH, Alam K, Shahin KI, Farid DM. A deep learning approach for network intrusion classification. In: 2024 IEEE Region 10 Symposium (TENSYMP); 2024 Sep; 1–6. IEEE.
[14] AboulEla S, Kashef R. Enhancing IoT intrusion detection with transformer-based network traffic classification. In: 2025 IEEE International Systems Conference (SysCon); 2025 Apr; 1–8. IEEE.
[15] Alam K, Monir MF, Hassan Z, Habib MT. Optimizing IoT network intrusion detection: A deep learning approach. In: 2024 7th Conference on Cloud and Internet of Things (CIoT); 2024 Oct; 1–5. IEEE.
[16] Luqman M, Zeeshan M, Riaz Q, Hussain M, Tahir H, Mazhar N, Khan MS. Intelligent parameter-based in-network IDS for IoT using UNSW-NB15 and BoT-IoT datasets. Journal of the Franklin Institute. 2025;362(1):107440.
[17] Jablaoui R, Liouane N. Network security based combined CNN-RNN models for IoT intrusion detection system. Peer-to-Peer Networking and Applications. 2025;18(3):129.
[18] Ma H, Zhang W, Zhang D, Chen B. An IoT intrusion detection framework based on feature selection and large language models fine-tuning. Scientific Reports. 2025;15(1):21158.
[19] Kamal H, Mashaly M. Robust intrusion detection system using an improved hybrid deep learning model for binary and multi-class classification in IoT networks. Technologies. 2025;13(3).
[20] Leni AES, Anand R, Mythili N, Pugalenthi R. An improved cyber-attack detection and classification model for IoT systems using fine-tuned deep learning model. International Journal of Sensor Networks. 2025;47(1):11–25.
[21] Silivery AK, Rao KRM, Solleti R. Dual-path feature extraction based hybrid intrusion detection in IoT networks. Computers and Electrical Engineering. 2025;122:109949.
[22] Rehman A, Alharbi O, Qasaymeh Y, Aljaedi A. DC-NFC: A custom deep learning framework for security and privacy in NFC-enabled IoT. Sensors. 2025;25(5):1381.
[23] Alam K, Monir MF, Hossain MJ, Uddin MS, Habib MT. Adaptive defense: Zero-day attack detection in NIDS with deep reinforcement learning. IEEE Access. 2025.
[24] UNSW-NB15 dataset. Available from: https://research.unsw.edu.au/projects/unsw-nb15-dataset
[25] BoT-IoT dataset. Available from: https://research.unsw.edu.au/projects/bot-iot-dataset
[26] ToN-IoT datasets. Available from: https://research.unsw.edu.au/projects/toniot-datasets
[27] Stephe S, Revathi V, Gunapriya B, Thirumalraj A. Blockchain-based private AI model with RPOA based sampling method for credit card fraud detection. In: Sustainable Development Using Private AI; 2025; 261–277. CRC Press.
[28] Punitha, P., Kumar, D. V., & Kumar, L. R. Advancing IoT security with an innovative machine learning paradigm for botnet attack detection. EAI Endorsed Transactions on Internet of Things, 2025; 11: Article e4521. https://doi.org/10.4108/eetiot.4521
[29] Ansar, N., Parveen, S., Khan, I. R., & Alankar, B. A scalable hybrid RF-BiLSTM framework for reliable IoT traffic threat detection via feature selection and temporal pattern recognition. EAI Endorsed Transactions on Internet of Things, 2025; 11: Article e10283. https://doi.org/10.4108/eetiot.10283
[30] Albarrak, A. M. An adaptive intrusion detection system for securing the Internet of Medical Things using deep learning. EAI Endorsed Transactions on Internet of Things, 2026; 11: Article e10326. https://doi.org/10.4108/eetiot.10326
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Narendra Kumar, Kalai Vani YS, Muneshwara M S, Chittibabulu Sape, V. Subba Reddy, Idimadakala Madhavilatha
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 4.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
