EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Attack-Level Failure Analysis of Invariant-Rule-Based Anomaly Detection in Industrial Control Systems

Geumhwan Cho

Mathematics · 05.06.2026 · 14 (11) · 2016

DOI: 10.3390/math14112016 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematics, online erschienen am 05.06.2026. Verfasst von Geumhwan Cho. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea government, Ministry of Trade, Industry & Energy, Korea University Grant.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Invariant-rule-based anomaly detection is attractive for industrial control systems (ICSs) because its rules are interpretable, auditable, and learnable from normal-operation data alone. However, mined invariants can miss attacks that induce weak, localized, transient, or rule-consistent deviations, because such attacks may not sufficiently violate the specific variable relationships captured by the rules. Aggregate time-step metrics can also obscure these failures, since they do not reveal which documented attack windows remain uncovered. Therefore, we analyze rule-only detection failures at the attack-window level and evaluate a rule-preserving hybrid detector that keeps the original invariant-rule alarm unchanged while adding learned anomaly evidence from per-sensor XGBoost residual models and an Anomaly Transformer. The final alarm uses OR fusion and matched-FPR results are reported as an evaluation-time operating-point analysis under a common system-level false-positive budget. On the SWaT benchmark, the reproduced rule-only detector detects 16/36 attacks at an attack-window recall threshold of 0.05 and 13/36 at 0.4. At the Zhu-matched evaluation-time false-positive budget (α≈0.00447), the pre-specified equal-weight hybrid reaches 19/36 and 16/36, respectively. For localization, SHAP attribution on the XGBoost residual models places the attacked sensor in the top-5 for 70.6% of direct sensor attacks and a variable from the correct process stage in the top-5 for 94.4% of all attacks. These results indicate that rule-preserving residual learning modestly improves attack-level coverage while providing operator-oriented localization evidence rather than definitive root-cause identification.

Förderung

  • Korea government
  • Ministry of Trade, Industry & Energy
  • Korea University Grant

Zitieren

APA

Cho, G. (2026). Attack-Level Failure Analysis of Invariant-Rule-Based Anomaly Detection in Industrial Control Systems. Mathematics, 14(11), 2016. https://doi.org/10.3390/math14112016

Vancouver

Cho G. Attack-Level Failure Analysis of Invariant-Rule-Based Anomaly Detection in Industrial Control Systems. Mathematics. 2026;14(11):2016. doi:10.3390/math14112016

BibTeX
@article{Cho2026,
  author = {Cho, Geumhwan},
  title = {Attack-Level Failure Analysis of Invariant-Rule-Based Anomaly Detection in Industrial Control Systems},
  journal = {Mathematics},
  year = {2026},
  volume = {14},
  number = {11},
  pages = {2016},
  doi = {10.3390/math14112016}
}
Kostenlos starten →