arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.08383cs.CV
收藏

AFGI:面向联邦学习中准确且快速收敛的梯度反演攻击

AFGI: Towards Accurate and Fast-convergent Gradient Inversion Attack in Federated Learning

Soochow University(苏州大学);Macquarie University(麦考瑞大学);University of Puerto Rico at Mayagüez(波多黎各大学马亚圭斯分校)

Can Liu, Jin Wang, and Yipeng Zhou, Yachao Yuan, Quanzheng Sheng, Kejie Lu

AI总结:

本文提出AFGI梯度反演攻击算法,通过标签恢复模块和VME正则化项解决重复标签下高分辨率图像重建精度差、收敛慢的问题,在ImageNet上减少85%时间成本并实现高质量重建。

摘要:

联邦学习(FL)通过仅暴露用户的模型梯度来实现模型训练中的隐私保护。然而,FL用户容易受到梯度反演攻击(GIAs)的威胁,这类攻击能够基于模型梯度重建真实训练数据(如图像)。但是,现有GIAs在重建高分辨率图像时面临两个挑战:精度较差和收敛缓慢,尤其是当训练批次中存在重复标签时。为应对这些挑战,我们提出了一种准确且快速收敛的梯度反演攻击算法,称为AFGI,其包含两个组成部分:标签恢复模块(LRB),能够基于暴露的梯度准确恢复私有图像中的重复标签;VME正则化项,其包括重建图像的全变差、三通道均值与边缘之间的差异、以及暴露梯度与重建图像所得数值之间的差异。AFGI可被视为一种白盒攻击策略,利用LRB恢复的标签来重建图像。特别地,AFGI效率很高,当用户训练批次大小达到48时仍能准确重建真实图像。我们的实验结果表明,AFGI在ImageNet数据集上能够减少85%的时间成本,同时实现卓越的反演质量。最后,我们的研究揭示了FL在隐私保护方面的不足,促使开发更先进的对抗策略。

英文摘要:

Federated learning (FL) empowers privacypreservation in model training by only exposing users' model gradients. Yet, FL users are susceptible to gradient inversion attacks (GIAs) which can reconstruct ground-truth training data such as images based on model gradients. However, reconstructing high-resolution images by existing GIAs faces two challenges: inferior accuracy and slow-convergence, especially when duplicating labels exist in the training batch. To address these challenges, we present an Accurate and Fast-convergent Gradient Inversion attack algorithm, called AFGI, with two components: Label Recovery Block (LRB) which can accurately restore duplicating labels of private images based on exposed gradients; VME Regularization Term, which includes the total variance of reconstructed images, the discrepancy between three-channel means and edges, between values from exposed gradients and reconstructed images, respectively. The AFGI can be regarded as a white-box attack strategy to reconstruct images by leveraging labels recovered by LRB. In particular, AFGI is efficient that accurately reconstruct ground-truth images when users' training batch size is up to 48. Our experimental results manifest that AFGI can diminish 85% time costs while achieving superb inversion quality in the ImageNet dataset. At last, our study unveils the shortcomings of FL in privacy-preservation, prompting the development of more advanced countermeasure strategies.

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。

↑