홈 › Papers

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

2026-04-23 · Guilin Deng, Silong Chen, Yuchuan Luo, Yi Liu, Songlei Wang, Zhiping Cai, Lin Liu, Xiaohua Jia, Shaojing Fu arxiv

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 $\href{https://anonymous.4open.science/r/Passive-MIA-5268}{link}$.

📄 PDF Abstract BibTeX arXiv:2604.21197

Code (0)

등록된 구현이 없습니다.

Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning

2018-12-03 · Milad Nasr, Reza Shokri, Amir Houmansadr

Deep neural networks are susceptible to various inference attacks as they remember information about their training data. We design white-box inference attacks to perform a comprehensive privacy analysis of deep learning…

Deep Learning Federated Learning

Leveraging Soft Prompts for Privacy Attacks in Federated Prompt Tuning

2026-01-10 · Quan Minh Nguyen, Min-Seon Kim, Hoang M. Ngo, Trong Nghia Hoang 외 arxiv

Membership inference attack (MIA) poses a significant privacy threat in federated learning (FL) as it allows adversaries to determine whether a client's private dataset contains a specific data sample. While defenses aga…

Federated Learning

Interaction-level Membership Inference Attack Against Federated Recommender Systems

2023-01-26 · Wei Yuan, Chaoqun Yang, Quoc Viet Hung Nguyen, Lizhen Cui 외

The marriage of federated learning and recommender system (FedRec) has been widely used to address the growing data privacy concerns in personalized recommendation services. In FedRecs, users' attribute information and b…

Attribute Federated Learning Inference Attack Membership Inference Attack+1

Differentially Private Data Generative Models

2018-12-06 · Qingrong Chen, Chong Xiang, Minhui Xue, Bo Li 외

Deep neural networks (DNNs) have recently been widely adopted in various applications, and such success is largely due to a combination of algorithmic breakthroughs, computation resource improvements, and access to a lar…

BIG-bench Machine Learning Federated Learning Inference Attack Membership Inference Attack

Evaluating Differential Privacy Against Membership Inference in Federated Learning: Insights from the NIST Genomics Red Team Challenge

2026-04-14 · Gustavo de Carvalho Bertoli arxiv

While Federated Learning (FL) mitigates direct data exposure, the resulting trained models remain susceptible to membership inference attacks (MIAs). This paper presents an empirical evaluation of Differential Privacy (D…

Federated Learning Red Teaming