paper-with-me

홈 › Papers

Unified Breakdown Analysis for Byzantine Robust Gossip

2024-10-14 · Renaud Gaucher, Aymeric Dieuleveut, Hadrien Hendrikx

In decentralized machine learning, different devices communicate in a peer-to-peer manner to collaboratively learn from each other's data. Such approaches are vulnerable to misbehaving (or Byzantine) devices. We introduce F-RG, a general framework for building robust decentralized algorithms with guarantees arising from robust-sum-like aggregation rules F. We then investigate the notion of *breakdown point*, and show an upper bound on the number of adversaries that decentralized algorithms can tolerate. We introduce a practical robust aggregation rule, coined CS+, such that CS+-RG has a near-optimal breakdown. Other choices of aggregation rules lead to existing algorithms such as ClippedGossip or NNA. We give experimental evidence to validate the effectiveness of CS+-RG and highlight the gap with NNA, in particular against a novel attack tailored to decentralized communications.

📄 PDF Abstract BibTeX arXiv:2410.10418

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Byzantine-Robust Decentralized Learning via ClippedGossip

2022-02-03 · Lie He, Sai Praneeth Karimireddy, Martin Jaggi

In this paper, we study the challenging task of Byzantine-robust decentralized training on arbitrary communication graphs. Unlike federated learning where workers communicate through a server, workers in the decentralize…

Federated Learning

Byzantine Fault-Tolerant Multi-Agent System for Healthcare: A Gossip Protocol Approach to Secure Medical Message Propagation

2025-11-27 · Nihir Chadderwala arxiv

Recent advances in generative AI have enabled sophisticated multi-agent architectures for healthcare, where large language models power collaborative clinical decision-making. However, these distributed systems face crit…

GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework

2025-04-24 · Yacine Belal, Mohamed Maouche, Sonia Ben Mokhtar, Anthony Simonet-Boulogne

Gossip Learning (GL) is a decentralized learning paradigm where users iteratively exchange and aggregate models with a small set of neighboring peers. Recent GL approaches rely on dynamic communication graphs built and m…

Model Poisoning

Robust Distributed Estimation: Extending Gossip Algorithms to Ranking and Trimmed Means

2025-05-23 · Anna van Elst, Igor Colin, Stephan Clémençon

This paper addresses the problem of robust estimation in gossip algorithms over arbitrary communication graphs. Gossip algorithms are fully decentralized, relying only on local neighbor-to-neighbor communication, making …

Secure Decentralized Federated Learning via Gossip and Virtual Voting

2026-07-09 · Amirhossein Taherpour, Xiaodong Wang arxiv

Decentralized federated learning (DFL) removes the central server by letting nodes exchange model updates through peer-to-peer gossip, but existing gossip-based methods often lack provenance finality and resilience to By…

Federated Learning