Guilin Deng, Silong Chen, Yuchuan Luo et al. · National University of Defense Technology · City University of Hong Kong +1 more
Gradient-based membership inference attack on federated LLMs achieving near-perfect accuracy via projection residual analysis
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 $\href{https://anonymous.4open.science/r/Passive-MIA-5268}{link}$.
Wenhao Jiang, Shaojing Fu, Yuchuan Luo et al. · National University of Defense Technology
Infers private labels in vertical federated learning by enumerating label permutations and comparing gradient cosine similarity, without auxiliary data
A typical Vertical Federated Learning (VFL) scenario involves several participants collaboratively training a machine learning model, where each party has different features for the same samples, with labels held exclusively by one party. Since labels contain sensitive information, VFL must ensure the privacy of labels. However, existing VFL-targeted label inference attacks are either limited to specific scenarios or require auxiliary data, rendering them impractical in real-world applications. We introduce a novel Label Enumeration Attack (LEA) that, for the first time, achieves applicability across multiple VFL scenarios and eschews the need for auxiliary data. Our intuition is that an adversary, employing clustering to enumerate mappings between samples and labels, ascertains the accurate label mappings by evaluating the similarity between the benign model and the simulated models trained under each mapping. To achieve that, the first challenge is how to measure model similarity, as models trained on the same data can have different weights. Drawing from our findings, we propose an efficient approach for assessing congruence based on the cosine similarity of the first-round loss gradients, which offers superior efficiency and precision compared to the comparison of parameter similarities. However, the computational cost may be prohibitive due to the necessity of training and comparing the vast number of simulated models generated through enumeration. To overcome this challenge, we propose Binary-LEA from the perspective of reducing the number of models and eliminating futile training, which lowers the number of enumerations from n! to n^3. Moreover, LEA is resilient against common defense mechanisms such as gradient noise and gradient compression.
ML Security Papers