Metraipolis › archive › dc_bc50c315944b

Matched-View Cross-Domain Evaluation of WireGuard VPN Traffic Classification Using Early-Flow Fingerprints — arXiv:2608.30000

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.30000
License (as archived)
CC0-1.0
Archived
2026-10-17T08:59:43.593Z
SHA-256 of the archived text
1798222b4c216dd25b4f1692941a0b8d0218cb87df6ef6617bbc99cc8c1891ac
Stable URL of this page
https://metraipolis.com/documento/dc_bc50c315944b

How to cite

Matched-View Cross-Domain Evaluation of WireGuard VPN Traffic Classification Using Early-Flow Fingerprints — arXiv:2608.30000 — arXiv (en), https://arxiv.org/abs/2608.30000 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bc50c315944b (Metraipolis archive dc_bc50c315944b, sha256 1798222b4c216dd25b4f1692941a0b8d0218cb87df6ef6617bbc99cc8c1891ac)
BibTeX
@misc{dcbc50c315944b,
  title = {Matched-View Cross-Domain Evaluation of WireGuard VPN Traffic Classification Using Early-Flow Fingerprints — arXiv:2608.30000},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.30000},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bc50c315944b; sha256 1798222b4c216dd25b4f1692941a0b8d0218cb87df6ef6617bbc99cc8c1891ac},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30000. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Classifying VPN-encrypted traffic by application category typically relies on datasets that collect non-VPN and VPN traffic in separate sessions, conflating encapsulation effects with session-level differences in user behavior, timing, and application mix. We use a recently published WireGuard tunnel dataset in which pre- and post-tunnel traffic is captured simultaneously, with a packet-level match ratio above 99.9%. This matched-capture design eliminates session-level confounds and enables a cross-domain benchmark: models are trained on non-VPN flows and tested on the VPN view of the same underlying flows. We compare whole-flow statistical aggregates (FlowFeatures) and Sequence of Packet Length and Time (SPLT) early-flow fingerprints across Random Forest, XGBoost, and a multi-scale CNN1D. Cross-domain transfer depends jointly on representation and model: tree ensembles achieve balanced accuracy of 0.84-0.93 with FlowFeatures but only 0.60-0.75 with flattened SPLT, whereas CNN1D processes the same SPLT fingerprint as a sequence and achieves the strongest transfer overall (balanced accuracy 0.98, macro F1 0.89) without any VPN data during training.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-01 in cs.NI).
Categorie arXiv: Networking and Internet Architecture (cs.NI).
Pagina del lavoro: https://arxiv.org/abs/2608.30000 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T08:37:15.978Z dalla pagina https://arxiv.org/catchup/cs.NI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).