Research Article

Traffic-to-Image-Based IoT Intrusion Detection: Multi-Dataset Performance and Efficiency Analysis

Volume: 9 Number: 1 October 25, 2026

Traffic-to-Image-Based IoT Intrusion Detection: Multi-Dataset Performance and Efficiency Analysis

Abstract

This study presents a unified traffic-to-image-based intrusion detection framework evaluated across three heterogeneous IoT/IIoT benchmark datasets: CICIoT2023, TON-IoT, and Edge-IIoTset. MobileViT-XXS, EfficientNet-B0, and Swin-Tiny were systematically compared in terms of classification performance and computational efficiency. Under the controlled class-wise window construction protocol, MobileViT-XXS achieved a macro-F1 of 98.12% on CICIoT2023, while Swin-Tiny reached 99.88% and 100% on Edge-IIoTset and TON-IoT, respectively. Five-seed experiments characterized performance variability across training runs, with mean macro-F1 scores of 97.21% for MobileViT-XXS on CICIoT2023 and 99.53% and 99.17% for Swin-Tiny on Edge-IIoTset and TON-IoT, respectively. Sensitivity analyses showed generally strong performance across alternative representation settings. However, under label-independent window construction, MobileViT-XXS macro-F1 on CICIoT2023 decreased to 35.72%, with a mean window purity of 12.75%, revealing a substantial limitation of the class-wise representation under heterogeneous traffic conditions. Efficiency analysis further showed that MobileViT-XXS provides substantially lower model size and parameter count than the larger architectures, while the reported latency and throughput measurements reflect performance on the NVIDIA A100 experimental platform. Overall, the results establish performance–efficiency trade-offs under controlled class-wise evaluation while highlighting the need for label-independent validation before drawing conclusions about practical intrusion detection performance.

Keywords

Supporting Institution

TÜBITAK

Thanks

This work is supported by The Scientific and Technological Research Council of Türkiye (TÜBİTAK) 1515 Frontier R&D Laboratories Support Program for Türk Telekom 6G R&D Lab under project number 5249902.

References

  1. Gyamfi, E., & Jurcut, A. (2022). Intrusion detection in Internet of Things systems: A review on design approaches leveraging multi-access edge computing, machine learning, and datasets. Sensors, 22(10), 3744. https://doi.org/10.3390/s22103744
  2. Liao, H., Murah, M. Z., Hasan, M. K., Aman, A. H. M., Fang, J., Hu, X., & Khan, A. U. R. (2024). A survey of deep learning technologies for intrusion detection in Internet of Things. IEEE Access, 12, 4745–4761. https://doi.org/10.1109/ACCESS.2023.3349287
  3. Neto, E. C. P., Dadkhah, S., Ferreira, R., Zohourian, A., Lu, R., & Ghorbani, A. A. (2023). CICIoT2023: A real-time dataset and benchmark for large-scale attacks in IoT environment. Sensors, 23(13), 5941. https://doi.org/10.3390/s23135941
  4. Ferrag, M. A., Friha, O., Hamouda, D., Maglaras, L., & Janicke, H. (2022). Edge-IIoTset: A new comprehensive realistic cyber security dataset of IoT and IIoT applications for centralized and federated learning. IEEE Access, 10, 40281–40306. https://doi.org/10.1109/ACCESS.2022.3165809
  5. Tseng, S. M., Wang, Y. Q., & Wang, Y. C. (2024). Multi-class intrusion detection based on Transformer for IoT networks using CIC-IoT-2023 dataset. Future Internet, 16(8), 284. https://doi.org/10.3390/fi16080284
  6. Ho, C. M. K., Yow, K. C., Zhu, Z., & Aravamuthan, S. (2022). Network intrusion detection via flow-to-image conversion and Vision Transformer classification. IEEE Access, 10, 97780–97793. https://doi.org/10.1109/ACCESS.2022.3200034
  7. Zhou, H., Zou, H., Li, W., Li, D., & Kuang, Y. (2025). HiViT-IDS: An efficient network intrusion detection method based on Vision Transformer. Sensors, 25(6), 1752. https://doi.org/10.3390/s25061752
  8. Tan, M., & Le, Q. V. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. Proceedings of the 36th International Conference on Machine Learning (ICML), 97, 6105–6114. https://proceedings.mlr.press/v97/tan19a.html

Details

Primary Language

English

Subjects

Artificial Intelligence (Other)

Journal Section

Research Article

Publication Date

October 25, 2026

Submission Date

September 4, 2026

Acceptance Date

October 15, 2026

Published in Issue

Year 2026 Volume: 9 Number: 1

APA
Toprak, A. G., Mercan, Ö. B., & Osmanca, M. S. (2026). Traffic-to-Image-Based IoT Intrusion Detection: Multi-Dataset Performance and Efficiency Analysis. Scientific Journal of Mehmet Akif Ersoy University, 9(1), 74-93. https://doi.org/10.70030/sjmakeu.2033131
AMA
1.Toprak AG, Mercan ÖB, Osmanca MS. Traffic-to-Image-Based IoT Intrusion Detection: Multi-Dataset Performance and Efficiency Analysis. Techno-Science. 2026;9(1):74-93. doi:10.70030/sjmakeu.2033131
Chicago
Toprak, Amine Gonca, Öykü Berfin Mercan, and Mustafa Serdar Osmanca. 2026. “Traffic-to-Image-Based IoT Intrusion Detection: Multi-Dataset Performance and Efficiency Analysis”. Scientific Journal of Mehmet Akif Ersoy University 9 (1): 74-93. https://doi.org/10.70030/sjmakeu.2033131.
EndNote
Toprak AG, Mercan ÖB, Osmanca MS (October 1, 2026) Traffic-to-Image-Based IoT Intrusion Detection: Multi-Dataset Performance and Efficiency Analysis. Scientific Journal of Mehmet Akif Ersoy University 9 1 74–93.
IEEE
[1]A. G. Toprak, Ö. B. Mercan, and M. S. Osmanca, “Traffic-to-Image-Based IoT Intrusion Detection: Multi-Dataset Performance and Efficiency Analysis”, Techno-Science, vol. 9, no. 1, pp. 74–93, Oct. 2026, doi: 10.70030/sjmakeu.2033131.
ISNAD
Toprak, Amine Gonca - Mercan, Öykü Berfin - Osmanca, Mustafa Serdar. “Traffic-to-Image-Based IoT Intrusion Detection: Multi-Dataset Performance and Efficiency Analysis”. Scientific Journal of Mehmet Akif Ersoy University 9/1 (October 1, 2026): 74-93. https://doi.org/10.70030/sjmakeu.2033131.
JAMA
1.Toprak AG, Mercan ÖB, Osmanca MS. Traffic-to-Image-Based IoT Intrusion Detection: Multi-Dataset Performance and Efficiency Analysis. Techno-Science. 2026;9:74–93.
MLA
Toprak, Amine Gonca, et al. “Traffic-to-Image-Based IoT Intrusion Detection: Multi-Dataset Performance and Efficiency Analysis”. Scientific Journal of Mehmet Akif Ersoy University, vol. 9, no. 1, Oct. 2026, pp. 74-93, doi:10.70030/sjmakeu.2033131.
Vancouver
1.Amine Gonca Toprak, Öykü Berfin Mercan, Mustafa Serdar Osmanca. Traffic-to-Image-Based IoT Intrusion Detection: Multi-Dataset Performance and Efficiency Analysis. Techno-Science. 2026 Oct. 1;9(1):74-93. doi:10.70030/sjmakeu.2033131