Toward Efficient Membership Inference Attacks against Federated Large Language Models: A Projection Residual Approach

TL;DR

This paper introduces ProjRes, a novel projection residuals-based membership inference attack that effectively exposes privacy vulnerabilities in federated large language models, outperforming existing methods.

Contribution

The paper presents ProjRes, the first efficient passive MIA tailored for FedLLMs that does not require shadow models or auxiliary data, revealing significant privacy risks.

Findings

ProjRes achieves near 100% attack accuracy.

It outperforms prior methods by up to 75.75%.

Remains effective under strong differential privacy defenses.

Abstract

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. To address this gap, we propose ProjRes, the first projection residuals-based passive MIA tailored for FedLLMs. ProjRes leverages hidden embedding vectors as sample representations and analyzes their projection residuals on the gradient subspace to uncover the intrinsic link between gradients and inputs. It requires no shadow models, auxiliary classifiers, or historical updates, ensuring efficiency and robustness. Experiments on four benchmarks and four LLMs show that ProjRes achieves near 100% accuracy, outperforming prior methods by up to 75.75%, and remains effective even under strong differential privacy defenses. Our findings reveal a previously overlooked privacy vulnerability in FedLLMs and call for a re-examination of their security assumptions. Our code and data are available at $\href{https://anonymous.4open.science/r/Passive-MIA-5268}{link}$.