Newest papers

Peer-Relative Trust-Guided Update Screening for Robust Semi-Decentralized Federated Learning under Label-Flipping Attacks

Ajay Kumar Shrestha, Sandhya Joshi · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.25714 · cited by 0 works (OpenAlex) · open-access PDF

Arabic

قد يقلل آليات الثقة والسمعة من تأثير العملاء الخبيثة في التعلم المشترك (FL) ، ولكن تحليل التحديث الصارم من الصعب تحت البيانات غير المستقلة والمستقلة (non-IID) لأن التحديثات المحلية الصحيحة قد تقلل مؤقتا من الأداء على عميل التحديث المشترك. استنادا إلى إطار عملنا السابق المشترك القائم على الثقة الصارم (SDFL) ، فإن هذه الوثيقة تستخدم إشارات الثقة وتشمل خمسة أنواع من التحديثات المرتبطة بتحديثات التحديثات المرتبطة بتحديثات التحديثات المشتركة التي تتوافق مع نوعية التحديثات المشتركة. يتم تقييم الطريقة مع 50 عميل MNIST ، 20٪ من المستخدم

Machine translation (Meta M2M100); the English original follows.

Abstract

Trust and reputation mechanisms can reduce the influence of malicious clients in federated learning (FL), but strict update filtering is difficult under non-independent and identically distributed (non-IID) data because honest local updates may temporarily reduce performance on a shared validation proxy. Building on our earlier trust-based semi-decentralized FL (SDFL) framework, this paper operationalizes the trust signals and introduces peer-relative update screening that combines a robust validation-utility score with direction- and norm-based update quality. The method is evaluated with 50 MNIST clients, 20% persistent label-flip attackers, Dirichlet heterogeneity levels of 0.5 and 0.1, 100 communication rounds, and five paired random seeds. Under moderate heterogeneity, the proposed method reaches 98.37% final accuracy while rejecting 95.82% of malicious updates and retaining 90.30% of benign updates; the final benign and malicious trust distributions are completely separated (KS=1.00). Under severe heterogeneity, it reaches 95.25% accuracy, rejects 88.55% of malicious updates, and retains 76.90% of benign updates (KS=0.96). Trust weighting alone preserves slightly higher utility in the most heterogeneous condition, but accepts all malicious submis-sions. The results therefore distinguish influence mitigation from explicit containment and quantify the utility-selectivity trade-off introduced by screening. The study provides an empirically validated off-chain governance core that can feed blockchain-based audit and incentive layers in SDFL.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Weighting, Reputation, Federated learning, Independent and identically distributed random variables, Audit

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange