Federated Transformer-DNN for Botnet Detection in Edge-IoT
DOI:
https://doi.org/10.29284/vgwwzp17Keywords:
Reinforcement Learning (RL), Federated Learning (FL), Deep Q-Network (DQN), Federated Averaging (FedAvg), Transformer-Deep Neural Network (Transformer-DNN), Botnet Detection, IoT, Edge Computing.Abstract
The rapid growth of the Internet of Things (IoT) has introduced significant security challenges, particularly due to the rise in botnet attacks targeting distributed networks. This study investigates Intrusion Detection Systems (IDS) utilizing the IoT23 dataset, focusing on addressing these challenges at the Edge of Things. A novel hybrid model, combining Deep Q-Networks (DQN) and Transformer-Deep Neural Networks (Transformer-DNN), is proposed to enhance botnet attack detection. The Transformer-DNN excels at identifying complex data patterns, while integration with DQN within a federated learning framework ensures an optimal balance between performance and resource efficiency. In comparison to ResNet-GRU models in federated learning, this study demonstrates the superiority of the DQN and Transformer-DNN hybrid. Seamlessly integrated with the FedAvg algorithm, the model addresses privacy and data-sharing limitations. Meticulous hyperparameter tuning, including a learning rate of 0.008 and an epsilon decay rate of 0.98, ensures effective learning. Model pruning further optimizes deployment for resource-constrained Edge of Things environments. The proposed hybrid model achieves an impressive accuracy of 98%, precision of 98%, recall of 97%, and an F1 score of 98%, with computations completed in 1689 seconds. This work highlights the hybrid model’s potential to outperform existing frameworks for precise and efficient botnet detection.
References
1. G. Bovenzi, G., Aceto, G., Ciuonzo, D., Montieri, A., Persico, V., & Pescap´e, A. (2023). Network anomaly detection methods in IoT environments via deep learning: A fair comparison of performance and robustness. Computers & Security, 128, 103167.
2. Ullah, I., & Mahmoud, Q. H. (2021). Design and development of a deep learning-based model for anomaly detection in IoT networks. IEEE Access, 9, 103906–103926.
3. Abdalgawad, N., Sajun, A., Kaddoura, Y., Zualkernan, I. A., & Aloul, F. (2021). Generative deep learning to detect cyberattacks for the IoT-23 dataset. IEEE Access, 10, 6430–6441.
4. R. Ullah, I., Ullah, A., & Sajjad, M. (2021). Towards a hybrid deep learning model for anomalous activities detection in internet of things networks. IoT, 2 (3), 428–448.
5. Y. Aversano, L., Bernardi, M. L., Cimitile, M., Pecori, R., & Veltri, L. (2021). Effective anomaly detection using deep learning in IoT systems. Wireless Communications and Mobile Computing, 2021, 9054336.
6. Douiba, M., Benkirane, S., Guezzaz, A., & Azrour, M. (2023). An improved anomaly detection model for IoT security using decision tree and gradient boosting. The Journal of Supercomputing, 79 (3),3392–3411.
7. Douiba, M., Benkirane, S., Guezzaz, A., & Azrour, M. (2023). Anomaly detection model based on gradient boosting and decision tree for IoT environments security. Journal of Reliable Intelligent Environments, 9 (4), 421–432.
8. Tahir, M., & Ali, M. I. (2022). On the performance of federated learning algorithms for IoT. IoT, 3 (2), 273–284.
9. Khan, L. U., Saad, W., Han, Z., Hossain, E., & Hong, C. S. (2021). Federated learning for internet of things: Recent advances, taxonomy, and open challenges. IEEE Communications Surveys & Tutorials,23 (3), 1759–1799.
10. Lian, Z., & Su, C. (2022). Decentralized federated learning for internet of things anomaly detection. In Proceedings of the 2022 ACM on Asia Conference on Computer and Communications Security (pp. 1249–1251).
11. KS, N., Nehemiah, K. H., Jane, N. Y., & Arputharaj, K. (2023). Clinical dataset classification using featureranking and satin bower bird optimized SVMs. The Computer Journal. Advance online publication. https://doi.org/10.1093/comjnl/
bxad118.
12. Navin, K. S., Nehemiah, H. K., Jane, Y. N., & Saroji, H. V. (2023). A classification framework using filter–wrapper based feature selection approach for the diagnosis of congenital heart failure. Journal of Intelligent & Fuzzy Systems, 44 (4), 6183–6218.
13. Ruzafa-Alc´azar, P., Fern´andez-Saura, P., M´armol-Campos, E., Gonz´alez-Vidal, A., Hern´andez-Ramos,J. L., Bernal-Bernabe, J., & Skarmeta, A. F. (2021). Intrusion detection based on privacy-preserving federated learning for the industrial IoT. IEEE Transactions on Industrial Informatics, 19 (2), 1145–1154.
14. Ullah, I., & Mahmoud, Q. H. (2022). Design and development of RNN anomaly detection model for IoT networks. IEEE Access, 10, 62722–62750.
15. Ullah, I., & Mahmoud, Q. H. (2022). An anomaly detection model for IoT networks based on flow and flag features using a feed-forward neural network. In 2022 IEEE 19th Annual Consumer Communications & Networking Conference (CCNC) (pp. 363–368). IEEE..
16. Saba, T., Rehman, A., Sadad, T., Kolivand, H., & Bahaj, S. A. (2022). Anomaly-based intrusion detection system for IoT networks through deep learning model. Computers and Electrical Engineering,99, 107810.
17. Nascita, A., Cerasuolo, F., Di Monda, D., Aberia Garcia, J. T., Montieri, A., & Pescap´e, A. (2022). Machine and deep learning approaches for IoT attack classification. In IEEE INFOCOM 2022-IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) (pp. 1–6). IEEE.
18. Al Sawafi, Y., Touzene, A., & Hedjam, R. (2023). Hybrid deep learning-based intrusion detection system for RPL IoT networks. Journal of Sensor and Actuator Networks, 12 (2), 21.
19. Jithish, J., Alangot, B., Mahalingam, N., & Yeo, K. S. (2023). Distributed anomaly detection in smart grids: A federated learning-based approach. IEEE Access, 11, 7157–7179.
20. Kao, M.-T., Sung, D.-Y., Kao, S.-J., & Chang, F.-M. (2022). A novel two-stage deep learning structure for network flow anomaly detection. Electronics, 11 (10), 1531.
21. Rejito, J., Stiawan, D., Alshaflut, A., & Budiarto, R. (2024). Machine learning-based anomaly detection for smart home networks under adversarial attack. Computer Science and Information Technologies, (2), 122–129.
22. Balega, M., Farag, W., Wu, X.-W., Ezekiel, S., & Good, Z. (2024). Enhancing IoT security: Optimizing anomaly detection through machine learning. Electronics, 13 (11), 2148.
23. Nascita, A., Carillo, R., Giampetraglia, F., Iacono, A., Persico, V., & Pescap´e, A. (2024). Interpretability and complexity reduction in IoT network anomaly detection via XAI. In 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) (pp. 325–329). IEEE.
24. Nguyen, Q. H., Hore, S., Shah, A., Le, T., & Bastian, N. D. (2025). FedNIDS: A federated learning framework for Packet-based network intrusion detection system. Digital Threats: Research and Practice, 6(1), 1-23.
25. EA, M. A. (2023). A novel paradigm for IoT security: ResNet-GRU model revolutionizes botnet attack detection. International Journal of Advanced Computer Science & Applications, 14 (12).
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
