arXiv 2409.072912024-09-11cs.LGcs.AIcs.CRcs.CVstat.ML

探索基于扩散先验的用户级梯度反演

Exploring User-level Gradient Inversion with a Diffusion Prior

Vanderbilt University（范德堡大学）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Mitsubishi Electric Research Laboratories（三菱电机研发实验室）；Vanderbilt University Medical Center（范德堡大学医学中心）

Zhuohang Li, Andrew Lowy, Jing Liu, Toshiaki Koike-Akino, Bradley Malin, Kieran Parsons, Ye Wang

备注：: Presented at the International Workshop on Federated Learning in the Age of Foundation Models in conjunction with NeurIPS 2023

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本研究针对分布式学习场景，提出一种以去噪扩散模型为图像先验的用户级梯度反演攻击，可在大批量设置下恢复含用户隐私属性的代表性人脸图像，拓展了梯度反演的攻击面。

摘要：

我们将用户级梯度反演作为分布式学习中的一个新攻击面展开探索。首先，我们研究了现有攻击在推断训练数据重构之外的隐私信息方面的能力。受现有方法重构质量较低的启发，我们提出了一种新型梯度反演攻击，该攻击将去噪扩散模型用作强图像先验，以提升大批量场景下的恢复效果。传统攻击旨在重构单个样本，在大批量和大图像尺寸下效果不佳，而我们的方法与之不同，旨在恢复一张具有代表性的图像，该图像能够捕捉与底层用户对应的敏感共享语义信息。我们针对人脸图像开展的实验表明，我们的方法能够恢复逼真的人脸图像以及用户的隐私属性。

英文摘要：

We explore user-level gradient inversion as a new attack surface in distributed learning. We first investigate existing attacks on their ability to make inferences about private information beyond training data reconstruction. Motivated by the low reconstruction quality of existing methods, we propose a novel gradient inversion attack that applies a denoising diffusion model as a strong image prior in order to enhance recovery in the large batch setting. Unlike traditional attacks, which aim to reconstruct individual samples and suffer at large batch and image sizes, our approach instead aims to recover a representative image that captures the sensitive shared semantic information corresponding to the underlying user. Our experiments with face images demonstrate the ability of our methods to recover realistic facial images along with private user attributes.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。