Exploiting gradient leakage to reconstruct supposedly private training data, gradient inversion attacks are an ubiquitous threat in collaborative learning of neural networks. To prevent gradient leakage without suffering from severe loss in model performance, recent work proposed a PRivacy EnhanCing mODulE (PRECODE) based on variational modeling as extension for arbitrary model architectures. In this work, we investigate the effect of PRECODE on gradient inversion attacks to reveal its underlying working principle. We show that variational modeling induces stochasticity on PRECODE's and its subsequent layers' gradients that prevents gradient attacks from convergence. By purposefully omitting those stochastic gradients during attack optimization, we formulate an attack that can disable PRECODE's privacy preserving effects. To ensure privacy preservation against such targeted attacks, we propose PRECODE with Partial Perturbation (PPP), as strategic combination of variational modeling and partial gradient perturbation. We conduct an extensive empirical study on four seminal model architectures and two image classification datasets. We find all architectures to be prone to gradient leakage, which can be prevented by PPP. In result, we show that our approach requires less gradient perturbation to effectively preserve privacy without harming model performance.
翻译:利用梯度渗漏来重建所谓的私人培训数据,梯度反向攻击是合作学习神经网络时普遍存在的威胁。为了防止梯度渗漏,同时又不因模型性能严重损失而蒙受严重损失,最近的工作提议以变异模型为基础,作为任意模型结构的延伸,采用PRECODE(PRECODE) 来扩大梯度渗漏,以重建所谓的私人培训数据。在这项工作中,我们调查PRECODE(PRECODE)对梯度反向攻击的影响,以揭示其基本的工作原则。我们表明,变异模型对PRECODE(P)及其随后的层梯度进行广泛的经验研究,防止梯度攻击趋同。我们发现,在攻击优化期间,通过有意省略这些随机梯度梯度梯度梯度梯度梯度,我们设计了一种能够使PRECODE的隐私保护效果失效的攻击。为了确保隐私不受这种有针对性的攻击,我们建议PRECODE(PP),作为变异性模型和部分梯度渗透的战略组合。我们对四个半度模型和两个图像分类数据集进行广泛的实验研究。我们发现所有建筑结构都容易在攻击梯度渗漏,我们无法通过购买力平价来证明我们如何保持。