论文标题
对联邦学习的攻击：响应式Web用户界面，以从用户渐变中恢复培训数据
Attacks to Federated Learning: Responsive Web User Interface to Recover Training Data from User Gradients
论文作者
论文摘要
当地差异隐私（LDP）是保护单个用户数据的新兴隐私标准。可以应用有力的一种情况是一种情况，是联合学习，每个用户将其用户渐变发送给使用这些梯度执行随机梯度下降的聚合器。如果聚合器不受信任并且不应用于每个用户渐变，则聚合器可以从这些梯度中恢复敏感的用户数据。在本文中，我们提出了一个新的交互式Web演示，通过使用当地差异隐私可视化联合学习，展示了当地差异隐私的力量。此外，实时演示显示了LDP如何防止不受信任的聚合器恢复敏感训练数据。还创建了一种称为Exp-Hamming Recovery的度量，以显示聚合器可以恢复的数据的程度。
Local differential privacy (LDP) is an emerging privacy standard to protect individual user data. One scenario where LDP can be applied is federated learning, where each user sends in his/her user gradients to an aggregator who uses these gradients to perform stochastic gradient descent. In a case where the aggregator is untrusted and LDP is not applied to each user gradient, the aggregator can recover sensitive user data from these gradients. In this paper, we present a new interactive web demo showcasing the power of local differential privacy by visualizing federated learning with local differential privacy. Moreover, the live demo shows how LDP can prevent untrusted aggregators from recovering sensitive training data. A measure called the exp-hamming recovery is also created to show the extent of how much data the aggregator can recover.
