Metraipolis › archive › dc_d0a698b70567
Adversarial Robustness Is Not Zero-Day Generalization: A Controlled Evaluation of Flow-Based Intrusion Detectors on Corrected CIC-IDS2017 — arXiv:2611.00713
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.00713
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:32:55.701Z
- SHA-256 of the archived text
43673087cb6034caba59ac676ea64ffba42f462a1428fb1837b8ceb0cfe88411- Stable URL of this page
https://metraipolis.com/documento/dc_d0a698b70567
How to cite
Adversarial Robustness Is Not Zero-Day Generalization: A Controlled Evaluation of Flow-Based Intrusion Detectors on Corrected CIC-IDS2017 — arXiv:2611.00713 — arXiv (en), https://arxiv.org/abs/2611.00713 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d0a698b70567 (Metraipolis archive dc_d0a698b70567, sha256 43673087cb6034caba59ac676ea64ffba42f462a1428fb1837b8ceb0cfe88411)
BibTeX
@misc{dcd0a698b70567,
title = {Adversarial Robustness Is Not Zero-Day Generalization: A Controlled Evaluation of Flow-Based Intrusion Detectors on Corrected CIC-IDS2017 — arXiv:2611.00713},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.00713},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d0a698b70567; sha256 43673087cb6034caba59ac676ea64ffba42f462a1428fb1837b8ceb0cfe88411},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00713. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Synthetic variants of known attacks, including feature-space adversarial perturbations, are sometimes used as stand-ins for unseen ("zero-day") attacks when evaluating machine-learning network intrusion detection systems (NIDS). We test whether this proxy holds. On the corrected CIC-IDS2017 release we train Random Forest, XGBoost, a 1D-CNN and an FT-Transformer and compare, at a fixed 1% false-positive rate over five seeds, detection under constrained perturbations of known attacks (gradient-based and black-box attacks on 42 attacker-controllable features) with leave-one-attack-family-out (LOAO) detection, where an entire family is absent from training. Detection under the strongest perturbation we tested, with budgets of at most 0.2, stays between 90.9% and 99.7%, yet mean detection of held-out families falls to 76.2% (RF), 40.2% (XGBoost), 25.8% (1D-CNN) and 22.8% (FT-Transformer). Robustness exceeds LOAO detection for every model (gaps of 24 to 72 percentage points, 23 to 66 when robustness is also averaged over families; Holm-adjusted p $\le$ 0.00096), and the two measures agree at most on a coarse ranking of the models. An exact mixed-integer evasion search confirms the tree ensembles' scores. Benign-only anomaly detectors and a simple multi-class open-set baseline do not close the gap. A temporal split on 5 seeds (3 of the 4 models) leaves the gap in place. On CSE-CIC-IDS2018 the gap recurs for every model (16 to 68 points). On these benchmarks and under this threat model, a robustness score should not be read as a zero-day score, and the two should be reported separately. Code and per-seed results are publicly available.
Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.00713 — 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 2026-11-03T18:12:23.770Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).