Quantization-Aware Training for Man-in-the-Middle Attacks Detection in IoT Application
Main Article Content
Abstract
Issues in securing the resilience of Deep Learning models and operational problems related to model size and latency in the Internet of Things (IoT) environment, especially when applied to devices with limited resources, can be overcome by implementing a modified Quantization-Aware Training (QAT) model based on IDS and an autoencoder. This research proposes the use of QAT to achieve operational efficiency while strengthening the detection model’s resilience against data manipulation in MiTM attacks. By integrating QAT, the model not only becomes lighter for edge devices but also more capable of maintaining detection integrity even when model weights are compromised. The research was conducted using the CICIoT2023 dataset, and the output of the advanced QAT model was then applied to resource-constrained IoT devices, namely the Raspberry Pi 3. The methodology began with data collection, followed by data preprocessing, which was then normalized before being fed into the IDS and autoencoder techniques. After the autoencoder model was successfully created, the QAT model was developed so that it remained unchanged or even improved when implemented on the Raspberry Pi 3. With the application of QAT modifications, an 80.43% reduction in model size and an 11.2% increase in model inference speed were confirmed. Furthermore, when faced with QAT model weight corruption of up to 20%, the F1-score value remained stable at 100%. These results show that the QAT model is highly effective at improving model reliability and maintaining the resilience of deep learning models against MiTM attacks, even under limited conditions.
Article Details
References
[1] M. Zaman, N. Puryear, S. Abdelwahed, and N. Zohrabi, “A review of iot-based smart city development and management,” Smart Cities, vol. 7, no. 3, pp. 1462–1501, 2024.
[2] M. M. Cherian and S. L. Varma, “Mitigation of ddos and mitm attacks using belief based secure correlation approach in sdn-based iot
networks,” International Journal of Computer Network and Information Security, vol. 15, no. 1, p. 52, 2022.
[3] H. Fereidouni, O. Fadeitcheva, and M. Zalai, “Iot and man-in-the-middle attacks,” Security and Privacy, vol. 8, no. 2, p. e70016, 2025.
[4] S. Ryu, J. Yim, J. Seo, Y. Yu, and H. Seo, “Quantile autoencoder with abnormality accumulation for anomaly detection of multivariate sensor data,” IEEE Access, vol. 10, pp. 70428–70439, 2022.
[5] G. Trappolini, A. Purificato, F. Siciliano, L. D’Addona, A. M. Spagnolo, D. Dato, and F. Silvestri, “Quantized auto encoder-based anomaly detection for multivariate time series data in 5g networks,” IEEE Access, 2025.
[6] M. Rahmati, “Energy-aware federated learning for secure edge computing in 5g-enabled iot networks,” Journal of Electrical Systems and Information Technology, vol. 12, no. 1, p. 13, 2025.
[7] E. Hernandez-Laredo, ´A. G. Est´evez-Pedraza, L. M. Santiago-Fuentes, and L. Parra-Rodr´ıguez, “Optimizing fall risk diagnosis in older adults using a bayesian classifier and simulated annealing,” Bioengineering, vol. 11, no. 9, p. 908, 2024.
[8] S. Jena, A. Pulkit, K. Singh, A. Banerjee, S. Joshi, A. Ganesh, D. Singh, and A. Bhavsar, “Unified anomaly detection methods on edge device using knowledge distillation and quantization,” in International Workshop on Reproducible Research in Pattern Recognition, pp. 60–81, Springer, 2024.
[9] A. Michelena, J. Aveleira-Mata, E. Jove, M. Bay´on-Guti´errez, P. Novais, O. F. Romero, J. L. Calvo-Rolle, and H. Al´aiz-Moret´on, “A novel in-
telligent approach for man-in-the-middle attacks detection over internet of things environments based on message queuing telemetry transport,” Expert Systems, vol. 41, no. 2, p. e13263, 2024.
[10] A. M. Al-Ghamdi and M. M. Alansari, “Enhancing iot security: A comparative study of cnn and rnn-based anomaly detection using the ciciot2023 dataset.,” IAENG International Journal of Computer Science, vol. 52, no. 5, 2025.
[11] M. M. Khan and M. Alkhathami, “Anomaly detection in iot-based healthcare: machine learning for enhanced security,” Scientific Reports, vol. 14, no. 1, p. 5872, 2024.
[12] V. Kandasamy and A. A. Roseline, “Harnessing advanced hybrid deep learning model for real-time detection and prevention of man-in-the-middle cyber attacks,” Scientific Reports, vol. 15, no. 1, p. 1697, 2025.
[13] H. Q. Gheni and W. L. Al-Yaseen, “Two-step data clustering for improved intrusion detection system using cic-iot2023 dataset,” e-Prime Advances in Electrical Engineering, Electronics and Energy, vol. 9, p. 100673, 2024.
[14] M. Sliwka, M. Wojcik, and B. Kurek, “A comparative analysis of anomaly detection methods in iot networks: An experimental study,”
Sensors, vol. 14, no. 24, p. 11545, 2024
[15] Y. Li, Y. Qian, Y. Yu, X. Qin, C. Zhang, Y. Liu, K. Yao, J. Han, J. Liu, and E. Ding, “Structext: Structured text understanding with multi-modal transformers,” in Proceedings of the 29th ACM international conference on multimedia, pp. 1912–1920, 2021.
[16] I. Muraina, “Ideal dataset splitting ratios in machine learning algorithms: general concerns for data scientists and data analysts,” in 7th international Mardin Artuklu scientific research conference, pp. 496–504, 2022.
[17] A. Hassan, H. Khan, I. Uddin, A. Sajid, et al., “Optimal emerging trends of deep learning technique for detection based on convolutional neural network,” Bulletin of Business and Economics (BBE), vol. 12, no. 4, pp. 264–273, 2023.
[18] K. Yu, J. Zhu, W. Yuan, Q. Zhou, G. Xue, G. Wu, X. Wang, and X. Li, “Two-channel six degrees of freedom grating-encoder for precision positioning of sub-components in synthetic-aperture optics,” Optics express, vol. 29, no. 14, pp. 21113–21128, 2021.
[19] A. Ashraf, N. M. Nawi, T. Shahzad, M. Aamir, M. A. Khan, and K. Ouahada, “Dimension reduction using dual-featured auto-encoder for the histological classification of human lungs tissues,” IEEE access, 2024.
[20] X. Zhang, J. Wu, F. Zhang, Z. Lin, and M. Lu, “Histopathological image classification using novel convolutional autoencoder with residual connection,” Journal of Healthcare Engineering, vol. 2022, p. 6496942, 2022.
[21] Y. Wang, J. Chen, and F. Zhang, “Lightweight anomaly detection for edge devices using pruning and quantization,” in IEEE International Conference on Automation Science and Engineering (CASE), pp. 200–205, IEEE, 2023.
[22] B. Jacob, S. Kligys, B. Chen, M. Zhu, M. Tang, A. Howard, H. Adam, and D. Kalenichenko, “Quantization and training of neural networks for efficient integer-arithmetic-only inference,” Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2704–2713, 2018.
[23] S. Rani and R. Kaur, “Service quality models: A literature review,” Journal of Interdisciplinary Economic Research, vol. 5, no. 1, 2025.
[24] M. N. Almarri and E. A. Abu-Shanab, “Service quality measures: Systematic literature review and future research directions,” Journal of Internet and E-Business Studies, vol. 2021, no. 1, pp. 1–16, 2021.
[25] J. K. Alluhaibi and K. M. Ghazi, “Design and implementation of an internet-of-things-enabled smart meter and smart plug for home-energy-management system,” Electronics, vol. 12, no. 19, p. 4041, 2023.
[26] O. Rainio, J. Teuho, and R. Kl´en, “Evaluation metrics and statistical tests for machine learning,” Scientific Reports, vol. 14, no. 1, p. 6086, 2024.
[27] M. Orlando, A. Estebsari, E. Pons, M. Pau, S. Quer, M. Poncino, L. Bottaccioli, and E. Patti, “A smart meter infrastructure for smart
grid iot applications,” IEEE Internet of Things Journal, vol. 9, no. 14, pp. 12529–12541, 2021.