The classifier judged this item not relevant to AI security, so it is left out of lists, feeds, the API and dataset releases. If that is wrong, report a correction on this page.
InfoResearchPeer-reviewed
Leakage aware gated non local fusion network for calibrated IIoT SCADA cyberattack detection supporting cyber risk management and operational resilience
- Published
- Record updated
Summary
This study proposes the Gated Non-local Fusion Network (GNF), a compact tabular-flow model for five-class intrusion detection on the cleaned WUSTL-IIoT-2021 dataset, with leakage-aware preprocessing and temperature-scaled calibration. On the benchmark, GNF reports 0.9998 accuracy, 0.9399 macro-F1 and 0.0042 expected calibration error using about 1.4 M parameters. The authors caution that the results should not be read as uniform detection across attack categories.