Role-Aware Multi-modal federated learning system for detecting phishing webpages

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Bo, Khan, Imran, White, Martin, Beloff, Natalia
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914096543170560
author Wang, Bo
Khan, Imran
White, Martin
Beloff, Natalia
author_facet Wang, Bo
Khan, Imran
White, Martin
Beloff, Natalia
contents We present a federated, multi-modal phishing website detector that supports URL, HTML, and IMAGE inputs without binding clients to a fixed modality at inference: any client can invoke any modality head trained elsewhere. Methodologically, we propose role-aware bucket aggregation on top of FedProx, inspired by Mixture-of-Experts and FedMM. We drop learnable routing and use hard gating (selecting the IMAGE/HTML/URL expert by sample modality), enabling separate aggregation of modality-specific parameters to isolate cross-embedding conflicts and stabilize convergence. On TR-OP, the Fusion head reaches Acc 97.5% with FPR 2.4% across two data types; on the image subset (ablation) it attains Acc 95.5% with FPR 5.9%. For text, we use GraphCodeBERT for URLs and an early three-way embedding for raw, noisy HTML. On WebPhish (HTML) we obtain Acc 96.5% / FPR 1.8%; on TR-OP (raw HTML) we obtain Acc 95.1% / FPR 4.6%. Results indicate that bucket aggregation with hard-gated experts enables stable federated training under strict privacy, while improving the usability and flexibility of multi-modal phishing detection.
format Preprint
id arxiv_https___arxiv_org_abs_2509_22369
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Role-Aware Multi-modal federated learning system for detecting phishing webpages
Wang, Bo
Khan, Imran
White, Martin
Beloff, Natalia
Machine Learning
Distributed, Parallel, and Cluster Computing
We present a federated, multi-modal phishing website detector that supports URL, HTML, and IMAGE inputs without binding clients to a fixed modality at inference: any client can invoke any modality head trained elsewhere. Methodologically, we propose role-aware bucket aggregation on top of FedProx, inspired by Mixture-of-Experts and FedMM. We drop learnable routing and use hard gating (selecting the IMAGE/HTML/URL expert by sample modality), enabling separate aggregation of modality-specific parameters to isolate cross-embedding conflicts and stabilize convergence. On TR-OP, the Fusion head reaches Acc 97.5% with FPR 2.4% across two data types; on the image subset (ablation) it attains Acc 95.5% with FPR 5.9%. For text, we use GraphCodeBERT for URLs and an early three-way embedding for raw, noisy HTML. On WebPhish (HTML) we obtain Acc 96.5% / FPR 1.8%; on TR-OP (raw HTML) we obtain Acc 95.1% / FPR 4.6%. Results indicate that bucket aggregation with hard-gated experts enables stable federated training under strict privacy, while improving the usability and flexibility of multi-modal phishing detection.
title Role-Aware Multi-modal federated learning system for detecting phishing webpages
topic Machine Learning
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2509.22369