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

DOI: 10.48550/arXiv.2610.25714 · open-access PDF

Korean

신뢰 및 명성 메커니즘은 연방 학습 (FL)에서 악성 클라이언트의 영향을 줄일 수 있지만, 비 독립적이고 동일하게 분포 된 (non-IID) 데이터에서 엄격한 업데이트 필터링은 정직한 로컬 업데이트가 공유 인증 프록시의 성능을 일시적으로 감소시킬 수 있기 때문에 어려울 수 있습니다.이 논문은 신뢰 기반 반 분산 FL (SDFL) 프레임워크를 기반으로 신뢰를 기반으로 한 우리의 이전 프레임워크를 구축하여 신뢰 신호를 실행화하고 강력한 인증 유틸리티 점수와 방향 및 규범 기반 업데이트 품질을 결합하는 피어 관련 업데이트 스크리닝을 도입합니다.

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

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

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.25714, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

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