AI RESEARCH
Toward Efficient Membership Inference Attacks against Federated Large Language Models: A Projection Residual Approach
arXiv CS.LG
•
ArXi:2604.21197v1 Announce Type: new Federated Large Language Models (FedLLMs) enable multiple parties to collaboratively fine-tune LLMs without sharing raw data, addressing challenges of limited resources and privacy concerns. Despite data localization, shared gradients can still expose sensitive information through membership inference attacks (MIAs). However, FedLLMs' unique properties, i.e. massive parameter scales, rapid convergence, and sparse, non-orthogonal gradients, render existing MIAs ineffective.