Problem
Research questions and friction points this paper is trying to address.
Decentralized Federated Learning
Global Model Consistency
Byzantine Adversaries
Model Poisoning Attacks
Model-Consistent Byzantine-Resilient Decentralized Federated Learning for Collaborative Missions
🤖 AI Summary
本文提出DFL-C架构，通过集成异步公共子集共识协议和双域信任评分机制解决去中心化联邦学习中模型一致性问题及拜占庭攻击。
📝 Abstract
Decentralized federated learning (DFL) is a promising paradigm for autonomous nodes to collaboratively train AI models without relying on a central server. However, existing DFL solutions do not guarantee global model consistency, a critical requirement for collaborative mission-critical scenarios where model divergence undermines decision uniformity and safety. This lack of consistency also amplifies vulnerability to Byzantine adversaries, who exploit the decentralized network topology and weak synchrony to perform equivocation and model poisoning attacks against individual victims.
This paper introduces DFL-C, a novel Byzantine-resilient DFL architecture that enables decentralized nodes to perform collaborative training with global model consistency. At its core, DFL-C integrates an asynchronous common subset (ACS) consensus protocol into the DFL workflow to ensure all nodes aggregate a uniform set of model updates to establish global model consistency, despite individual Byzantine equivocation. DFL-C further implements a dual-domain trust scoring mechanism to provide resilience against data-domain Byzantine manipulations including model poisoning attacks. This mechanism complements the consensus protocol, significantly reducing the latter's runtime. Our experimental results demonstrate that DFL-C maintains model accuracy while achieving global model consistency under Byzantine behaviors with moderate consensus overhead. Notably, when compared with the state-of-the-art DFL solution BALANCE (Fang et al.) that does not provide model consistency, DFL-C achieves better model accuracy against untargeted model poisoning attacks and comparable resilience against backdoor attacks, with the advantage widened under non-IID scenarios.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Decentralized Federated Learning
Asynchronous Common Subset Consensus
Byzantine-Resilient
Dual-Domain Trust Scoring
Global Model Consistency
🔎 Similar Papers
No similar papers found.
