Metraipolis › archive › dc_738a079ffd36

Leakage-free evaluation of residual graph convolutional networks for network intrusion detection — arXiv:2611.04660

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04660
License (as archived)
CC0-1.0
Archived
2026-11-04T12:40:53.798Z
SHA-256 of the archived text
8e9bd995e5c44352aded49c43e8077561f3bd4092aa9fa2c565979d941400912
Stable URL of this page
https://metraipolis.com/documento/dc_738a079ffd36

How to cite

Leakage-free evaluation of residual graph convolutional networks for network intrusion detection — arXiv:2611.04660 — arXiv (en), https://arxiv.org/abs/2611.04660 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_738a079ffd36 (Metraipolis archive dc_738a079ffd36, sha256 8e9bd995e5c44352aded49c43e8077561f3bd4092aa9fa2c565979d941400912)
BibTeX
@misc{dc738a079ffd36,
  title = {Leakage-free evaluation of residual graph convolutional networks for network intrusion detection — arXiv:2611.04660},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04660},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_738a079ffd36; sha256 8e9bd995e5c44352aded49c43e8077561f3bd4092aa9fa2c565979d941400912},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04660. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Graph neural networks are increasingly proposed for network intrusion detection, yet many reported results come from protocols in which test flows shape the graph used for training, duplicated flows sit on both sides of the split, or a single split is reported. This study measures what a residual graph convolutional network gains over simpler models once these sources of optimism are removed. CICIDS2017 and NF-UNSW-NB15-v2 were cleaned with label-aware removal of exact duplicates, removing 69% of NF-UNSW-NB15-v2 flows. Flows were linked in a nearest-neighbour graph built from training flows only, and validation and test flows were attached to their nearest training flows at prediction time. A two-layer residual network was compared with eight models under the same settings, including a nearest-neighbour vote over the same graph, gradient-boosted trees and a random forest, over three seeds that each draw a new split, with ablations, leave-one-family-out and feature-noise tests. On CICIDS2017 the residual network reached a binary F1 of 98.11% (SD 0.18) and on NF-UNSW-NB15-v2 90.57% (0.38), indistinguishable from a multilayer perceptron without the graph and from other graph networks. Tree ensembles were 1.48 to 1.57 F1 points higher on CICIDS2017 and led on the area under the precision-recall curve on both datasets; their CICIDS2017 multiclass macro-F1 reached 93.08% against 64.51%, a gap mainly from benign flows the residual network assigned to small attack classes. No ablation, including transductive graph construction, changed F1 beyond seed variation. Under Gaussian feature noise (SD 0.5), the residual network kept an F1 of 96.16%, while XGBoost fell to 0.67%. Under a leakage-controlled protocol, message passing over flow graphs adds no measurable accuracy over a perceptron, and tree ensembles remain stronger on both; the advantage of graph models lies in robustness to feature noise.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.04660 — 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 2026-11-04T12:29:47.299Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).