IoT Anomaly Traffic Detection Method Based on Transformer Encoder Architecture
DOI:
https://doi.org/10.63313/JCSFT.9081Keywords:
IoT Security, Anomaly Network Traffic Detection, Transformer Encoder, Self-Attention MechanismAbstract
The widespread deployment of IoT devices has made heterogeneous network traffic highly complex, making abnormal traffic detection vital for IoT security. This paper presents a Transformer-based IoT abnormal traffic detection method tailored to the long-range temporal correlation of IoT traffic and the drawbacks of existing approaches. It first builds traffic embeddings with learnable positional encoding to project raw traffic features into a high-dimensional space, then leverages Transformer multi-head self-attention to capture long-range dependencies by modeling temporal correlations in traffic sequences. Feature compression and residual enhancement modules are further adopted to lower model complexity and inference delay for resource-limited IoT terminals. Experiments verify that the scheme accurately identifies normal traffic and diverse anomalous attacks with outstanding detection accuracy and stability.
References
[1] Raza S, Wallgren L, Voigt T. SVELTE: Real-time intrusion detection in the Internet of Things[J]. Ad hoc networks, 2013, 11(8): 2661-2674.
[2] Doshi R, Apthorpe N, Feamster N. Machine learning ddos detection for consumer internet of things devices[C]//2018 IEEE security and privacy workshops (SPW). IEEE, 2018: 29-35.
[3] Meidan Y, Bohadana M, Shabtai A, et al. ProfilIoT: A machine learning approach for IoT device identification based on network traffic analysis[C]//Proceedings of the symposium on applied computing. 2017: 506-509.
[4] Ammar M, Russello G, Crispo B. Internet of Things: A survey on the security of IoT frameworks[J]. Journal of information security and Applications, 2018, 38: 8-27.
[5] Alauthman M. P2P bot detection using deep learning with traffic reduction schema[J]. Journal of Theoretical and Applied Information Technology, 2020, 98(15).
[6] Shone N, Ngoc T N, Phai V D, et al. A deep learning approach to network intrusion detection[J]. IEEE transactions on emerging topics in computational intelligence, 2018, 2(1): 41-50.
[7] Portela A L, Menezes R A, Costa W L, et al. Detection of iot devices and network anomalies based on anonymized network traffic[C]//NOMS 2023-2023 IEEE/IFIP Network Operations and Management Symposium. IEEE, 2023: 1-6.
[8] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[J]. Advances in neural information processing systems, 2017, 30.
[9] Koroniotis N, Moustafa N, Sitnikova E, et al. Towards the development of realistic botnet dataset in the internet of things for network forensic analytics: Bot-iot dataset[J]. Future Generation Computer Systems, 2019, 100: 779-796.
[10] Nguyen H, Kashef R. TS-IDS: Traffic-aware self-supervised learning for IoT Network Intrusion Detection[J]. Knowledge-Based Systems, 2023, 279: 110966.
[11] Dong H, Kotenko I. Multi-task learning for IoT traffic classification: a comparative analysis of deep autoencoders[J]. Future Generation Computer Systems, 2024, 158: 242-254.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 by author(s) and Erytis Publishing Limited.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
How to Cite
