AI RESEARCH
GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework
arXiv CS.AI
•
ArXi:2504.17471v2 Announce Type: replace-cross Gossip Learning (GL) is a decentralized learning paradigm where users iteratively exchange and aggregate models with a small set of neighboring peers. Recent approaches rely on dynamic communication graphs built using Random Peer Sampling (RPS) protocols which have been proven to accelerate convergence. However, we show that these approaches are vulnerable to a dual attack: Byzantine nodes can poison models and manipulate peer sampling to amplify their influence.