CAFE: Catastrophic Data Leakage in Vertical Federated Learning
CAFE: Catastrophic Data Leakage in Vertical Federated Learning
复制标题
DOI：
--
复制
发表时间：
2021-10
期刊：
影响因子：
--
通讯作者：
Xiao Jin;Pin-Yu Chen;Chia-Yi Hsu;Chia-Mu Yu;Tianyi Chen
中科院分区：
文献类型：
--
作者：
Xiao Jin;Pin-Yu Chen;Chia-Yi Hsu;Chia-Mu Yu;Tianyi Chen
最近的研究表明，在分布式机器学习系统（如联邦学习（FL））中部署的梯度共享机制可能会泄露私有训练数据。增加批处理大小以使数据恢复复杂化通常被视为防止数据泄漏的一种有前途的防御策略。在本文中，我们重新审视了这一防御前提，并提出了一种先进的数据泄漏攻击，并提供了理论依据，以有效地从共享聚合梯度中恢复批量数据。我们将提出的方法命名为垂直联邦学习中的灾难性数据泄漏（CAFE）。与现有的数据泄漏攻击相比，我们在垂直FL设置上的大量实验结果证明了CAFE在执行大规模数据泄漏攻击时的有效性，并提高了数据恢复质量。我们还提出了一种切实可行的缓解CAFE的对策。我们的研究结果表明，参与标准FL的私人数据，特别是垂直案例，从训练梯度中泄露的风险很高。我们的分析表明，在这些学习环境中存在前所未有的实际数据泄露风险。我们工作的代码可以在https://github.com/DeRafael/CAFE上找到。
Recent studies show that private training data can be leaked through the gradients sharing mechanism deployed in distributed machine learning systems, such as federated learning (FL). Increasing batch size to complicate data recovery is often viewed as a promising defense strategy against data leakage. In this paper, we revisit this defense premise and propose an advanced data leakage attack with theoretical justification to efficiently recover batch data from the shared aggregated gradients. We name our proposed method as catastrophic data leakage in vertical federated learning (CAFE). Comparing to existing data leakage attacks, our extensive experimental results on vertical FL settings demonstrate the effectiveness of CAFE to perform large-batch data leakage attack with improved data recovery quality. We also propose a practical countermeasure to mitigate CAFE. Our results suggest that private data participated in standard FL, especially the vertical case, have a high risk of being leaked from the training gradients. Our analysis implies unprecedented and practical data leakage risks in those learning settings. The code of our work is available at https://github.com/DeRafael/CAFE.