EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

C-GUARD: Context-Adaptive Conformal Gating for Improving Robustness Against Evasive Windows PE Malware

Muhammad Imran, Malik Al-Essa, Felice Franchini, Giuseppe Pirlo

Future Internet · 13.08.2026 · 18 (8) · 431

DOI: 10.3390/fi18080431 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Future Internet, online erschienen am 13.08.2026. Verfasst von Muhammad Imran und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of Bari Aldo Moro.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Machine Learning (ML)-based malware detectors perform exceptionally well on standard benchmarks, but their robustness to evasive malware remains fragile. On EMBER2024, strong tree-based models achieve high accuracy on clean test sets yet miss a large number of evasive Windows PE samples. Through SHAP-based explainability, matched error comparisons, feature-family analysis, and margin diagnostics on the validation split, we identify consistent attribution and decision-margin differences between baseline true negatives and false negatives. We further show that false negatives occur at different decision depths, including both near-boundary cases and samples misclassified with high benign confidence. We propose C-GUARD, a context-adaptive conformal gated detector that preserves the optimized high-performing baseline while selectively invoking an auxiliary rescue detector on a targeted subset of baseline negative predictions. C-GUARD combines out-of-fold rescue learning to distinguish baseline false negatives from true negatives with adaptive gating under an explicit false-positive budget. A one-sided intervention rule preserves all baseline malware decisions. On the EMBER2024 standard test set, C-GUARD recovers 178 additional malware samples at the cost of 82 additional false positives. On the evasive challenge set, it recovers 17 additional evasive malware samples.

Förderung

  • University of Bari Aldo Moro

Zitieren

APA

Imran, M., Al-Essa, M., Franchini, F., & Pirlo, G. (2026). C-GUARD: Context-Adaptive Conformal Gating for Improving Robustness Against Evasive Windows PE Malware. Future Internet, 18(8), 431. https://doi.org/10.3390/fi18080431

Vancouver

Imran M, Al-Essa M, Franchini F, Pirlo G. C-GUARD: Context-Adaptive Conformal Gating for Improving Robustness Against Evasive Windows PE Malware. Future Internet. 2026;18(8):431. doi:10.3390/fi18080431

BibTeX
@article{Imran2026,
  author = {Imran, Muhammad and Al-Essa, Malik and Franchini, Felice and Pirlo, Giuseppe},
  title = {C-GUARD: Context-Adaptive Conformal Gating for Improving Robustness Against Evasive Windows PE Malware},
  journal = {Future Internet},
  year = {2026},
  volume = {18},
  number = {8},
  pages = {431},
  doi = {10.3390/fi18080431}
}
Kostenlos starten →