EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

RankBridge: Privacy-Preserving Rank-Based Explanation Clustering for Heterogeneous Federated Phishing Detection

Panhapiseth Lim, Priyanka Kumar, Richard Zanni, Timothy Lambdin

Computation · 15.06.2026 · 14 (6) · 137

DOI: 10.3390/computation14060137 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computation, online erschienen am 15.06.2026. Verfasst von Panhapiseth Lim und 3 weiteren Autor:innen. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning lets organizations train a shared model without pooling private data. The standard method, Federated Averaging, requires all participants to use the same input features, a condition that fails in cross-sector phishing detection, where banks analyze URL structure and hospitals analyze email content. We present RankBridge, a system that groups participants by comparing ranked lists of SHapley Additive exPlanations (SHAP) feature importance rather than model weights or gradients. Each participant trains a local LightGBM model, extracts the top-K features by SHAP importance, and sends a 60-byte ranked list of feature indices to a central server. The server applies rank correlation and Ward’s hierarchical clustering to identify similarly threatened organizations. RankBridge operates in two modes: ModelShare, where models are also shared within each discovered group for prediction ensembling, and RankOnly, where the server returns only a group label and each participant keeps their model private. Across 32 participants in five organization types, RankBridge (ModelShare) achieves F1 =0.853 (AUC =0.926) on synthetic data and F1 =0.772 (AUC =0.812) on real phishing data, and it is the only method to outperform isolated local training on both. On real heterogeneous data the standard baselines adapted to LightGBM, including Federated Averaging, retain a moderate thresholded F1 (≈0.73) but their ranking quality collapses to near-random (AUC ≈0.59, PR-AUC ≈0.66), whereas RankBridge sustains AUC =0.812 and PR-AUC =0.819. RankBridge recovers the correct organizational groupings with Normalized Mutual Information (NMI) =0.973. The rank-based grouping channel itself transmits 60 bytes per participant per round, roughly 10,000× less than a full model upload.

Zitieren

APA

Lim, P., Kumar, P., Zanni, R., & Lambdin, T. (2026). RankBridge: Privacy-Preserving Rank-Based Explanation Clustering for Heterogeneous Federated Phishing Detection. Computation, 14(6), 137. https://doi.org/10.3390/computation14060137

Vancouver

Lim P, Kumar P, Zanni R, Lambdin T. RankBridge: Privacy-Preserving Rank-Based Explanation Clustering for Heterogeneous Federated Phishing Detection. Computation. 2026;14(6):137. doi:10.3390/computation14060137

BibTeX
@article{Lim2026,
  author = {Lim, Panhapiseth and Kumar, Priyanka and Zanni, Richard and Lambdin, Timothy},
  title = {RankBridge: Privacy-Preserving Rank-Based Explanation Clustering for Heterogeneous Federated Phishing Detection},
  journal = {Computation},
  year = {2026},
  volume = {14},
  number = {6},
  pages = {137},
  doi = {10.3390/computation14060137}
}
Kostenlos starten →