Mean FlowSpectrum: Enhancing Encrypted Traffic Classification via Mean-Based Similarity Correction
IEEE Access · 2026 · 14 · 122058-122086
DOI: 10.1109/access.2026.3722265 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Chanhyung Kim und 2 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Institute of Information and Communications Technology Planning and Evaluation (IITP) grant through by Korean Government [Ministry of Science and ICT (MSIT)], Development of Security Monitoring Technology Based Network Behavior Against Encrypted Cyber Threats in Information and Communications Technology (ICT) Converg…, National Research Foundation of Korea (NRF) grant through by Korean Government.
Abstract (Originalsprache)
As the majority of Internet traffic is now transmitted via encrypted protocols such as HTTPS, TLS 1.3, and VPNs, existing Deep Packet Inspection (DPI)-based security techniques are no longer able to operate effectively. Consequently, developing technologies capable of accurately classifying encrypted traffic without decryption is emerging as a core task in the field of network security. In this paper, Mean FlowSpectrum (Mean FS), a lightweight extension of the existing FlowSpectrum (FS) similarity rule, is proposed. Whereas FS uses only minimum distances between test samples and class spectra, Mean FS adds a class-mean consistency term to reduce errors caused by local spectral overlap. The method was evaluated with Semi-AE and Semi-2DCAE on ISCX-VPN2016, USTC-TFC2016, and a newly collected TLS 1.3/SSH attack-traffic testbed dataset. In a paired evaluation over five independent seeds, Mean FS improved macro F1-score in all six dataset–backbone combinations by 3.10–9.98 percentage points, and every paired improvement was statistically significant ( $p\lt 0.01$ ). Reducing the input size from $28\times 28$ to $16\times 16$ maintained comparable performance while improving memory efficiency, and Mean FS substantially mitigated the degradation caused by reducing the session size from $n=10$ to $n=1$ . GPU memory and inference time were measured for the model-side pipeline; end-to-end live-capture latency was outside the scope of this study. Mean FS therefore provides a lightweight extension to the FlowSpectrum decision rule. The measured results support its use as a decision-stage refinement for encrypted-traffic analysis, but operational validation with benign and mixed traffic is still required.
Förderung
- Institute of Information and Communications Technology Planning and Evaluation (IITP) grant through by Korean Government [Ministry of Science and ICT (MSIT)]
- Development of Security Monitoring Technology Based Network Behavior Against Encrypted Cyber Threats in Information and Communications Technology (ICT) Converg…
- National Research Foundation of Korea (NRF) grant through by Korean Government
Zitieren
APA
Kim, C., Kim, T., & Youn, J. M. (2026). Mean FlowSpectrum: Enhancing Encrypted Traffic Classification via Mean-Based Similarity Correction. IEEE Access, 14, 122058-122086. https://doi.org/10.1109/access.2026.3722265
Vancouver
Kim C, Kim T, Youn JM. Mean FlowSpectrum: Enhancing Encrypted Traffic Classification via Mean-Based Similarity Correction. IEEE Access. 2026;14:122058-122086. doi:10.1109/access.2026.3722265
BibTeX
@article{Kim2026,
author = {Kim, Chanhyung and Kim, Taeyun and Youn, Jonghee M.},
title = {Mean FlowSpectrum: Enhancing Encrypted Traffic Classification via Mean-Based Similarity Correction},
journal = {IEEE Access},
year = {2026},
volume = {14},
pages = {122058--122086},
doi = {10.1109/access.2026.3722265}
}
EUVIMED