Metraipolis › archive › dc_1e4d2ed17c50

Unmasking Shortcut Learning in IoT Intrusion Detection: A Forensic, Multi-Paradigm Evaluation of Feature Dependence and Data Leakage — arXiv:2609.28725

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.28725
License (as archived)
CC0-1.0
Archived
2026-10-08T04:53:18.410Z
SHA-256 of the archived text
dece74c38d83085577917cbc70bd81f26f9f84673cc02f96edcfcccfa43d7d3b
Stable URL of this page
https://metraipolis.com/documento/dc_1e4d2ed17c50

How to cite

Unmasking Shortcut Learning in IoT Intrusion Detection: A Forensic, Multi-Paradigm Evaluation of Feature Dependence and Data Leakage — arXiv:2609.28725 — arXiv (en), https://arxiv.org/abs/2609.28725 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1e4d2ed17c50 (Metraipolis archive dc_1e4d2ed17c50, sha256 dece74c38d83085577917cbc70bd81f26f9f84673cc02f96edcfcccfa43d7d3b)
BibTeX
@misc{dc1e4d2ed17c50,
  title = {Unmasking Shortcut Learning in IoT Intrusion Detection: A Forensic, Multi-Paradigm Evaluation of Feature Dependence and Data Leakage — arXiv:2609.28725},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.28725},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1e4d2ed17c50; sha256 dece74c38d83085577917cbc70bd81f26f9f84673cc02f96edcfcccfa43d7d3b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28725. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Machine learning-based Network Intrusion Detection Systems often report near-perfect performance on IoT benchmarks. However, whether these models learn generalizable attack behavior or exploit spurious dataset shortcuts- such as static testbed IP/MAC addresses and chronological recording artifacts-remains an important question. We evaluate the CyberFlowIoT-GICAP benchmark, containing 3,617,388 flow records across 126 PCAP sessions with 849,395 benign flows. Four learning paradigms are evaluated across four feature configurations using PCAP-disjoint splits; LightGBM is additionally evaluated using conventional random-flow splitting. When only statistical flow behavior is used (Fbehav), LightGBM (92.58% +/- 8.18%), Random Forest (92.59% +/- 8.18%), and Deep MLP (92.55% +/- 8.18%) achieve nearly identical Macro-F1, indicating that performance is constrained by feature representation rather than model complexity. With raw timestamps (Ftstamp), tree-based models reach 99.28% Macro-F1, while the linear model remains at 90.62%, showing that nonlinear models can exploit dataset-specific temporal structure. Attack detectability is highly asymmetric: high-rate and active attacks maintain >99.8% recall from flow behavior alone in nonlinear models, whereas the DNS Beaconing drops from 27.78% to 0.00% recall when contextual features are removed. Conventional random-flow splitting increases attack recall by up to 14.00%, highlighting the effect of placing flows from the same sessions in both training and test sets. We conclude with a 4-point protocol checklist for realistic IoT NIDS evaluation.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-25 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR) ; Machine Learning (cs.LG); Networking and Internet Architecture (cs.NI).
Pagina del lavoro: https://arxiv.org/abs/2609.28725 — 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 2026-10-08T04:30:43.801Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).