paperApril 2026Unreviewed

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

Guilin Deng, Silong Chen, Yuchuan Luo, Yi Liu, Songlei Wang, Zhiping Cai, Lin Liu, Xiaohua Jia, Shaojing Fu

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, w

Framework mappings

OWASP Top 10 for LLM Applications

LLM02Sensitive Information Disclosure

MITRE ATLAS

AML.T0024.000Infer Training Data Membership

Suggested from the entry's categories.

Cite

@misc{deng2026efficient,
  title = {{Toward Efficient Membership Inference Attacks against Federated Large Language Models: A Projection Residual Approach}},
  author = {Guilin Deng and Silong Chen and Yuchuan Luo and Yi Liu and Songlei Wang and Zhiping Cai and Lin Liu and Xiaohua Jia and Shaojing Fu},
  year = {2026},
  month = apr,
  eprint = {2604.21197},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.21197}
}