TOFU：通过将权重更新编码为代理数据梯度实现混淆联邦更新
TOFU: Towards Obfuscated Federated Updates by Encoding Weight Updates into Gradients from Proxy Data
AI总结：
本文提出 TOFU 算法，将客户端权重更新编码为类噪声代理数据的梯度进行传输，以降低联邦学习通信量并增强隐私，实验显示准确率损失小且效率显著提升。
摘要：
联邦学习的进展与丰富的用户数据，使多个客户端能够在不共享用户数据的情况下开展丰富的协同学习。这一过程通过中央服务器以权重更新的形式聚合学习结果来实现。然而，其代价是客户端与服务器之间反复进行昂贵通信，并引发对用户隐私受损的担忧。将梯度反演为生成这些梯度的数据被称为数据泄露。加密技术可用于抵御此类泄露，但会带来额外开销。为应对通信效率与隐私方面的挑战，我们提出 TOFU，这是一种新颖算法，可生成代理数据，并在其梯度中编码每个客户端的权重更新。此时共享的不再是权重更新，而是该代理数据。由于输入数据的维度复杂度远低于权重，这种编码使我们能够在每轮通信中发送少得多的数据。此外，代理数据类似噪声，即使数据泄露攻击实现完美重构，也只会将解码后的梯度反演为无法识别的噪声，从而增强隐私。我们表明，TOFU 在 MNIST 和 CIFAR-10 数据集上分别实现了低于 1% 和 7% 的准确率下降。这种下降可通过几轮昂贵的加密梯度交换得到恢复。这使我们能够在联邦设置中学习到接近完整的准确率，同时在 MNIST 和 CIFAR-10 上的通信效率分别比标准 Federated Averaging 算法高 4 倍和 6.6 倍。
英文摘要：
Advances in Federated Learning and an abundance of user data have enabled rich collaborative learning between multiple clients, without sharing user data. This is done via a central server that aggregates learning in the form of weight updates. However, this comes at the cost of repeated expensive communication between the clients and the server, and concerns about compromised user privacy. The inversion of gradients into the data that generated them is termed data leakage. Encryption techniques can be used to counter this leakage, but at added expense. To address these challenges of communication efficiency and privacy, we propose TOFU, a novel algorithm which generates proxy data that encodes the weight updates for each client in its gradients. Instead of weight updates, this proxy data is now shared. Since input data is far lower in dimensional complexity than weights, this encoding allows us to send much lesser data per communication round. Additionally, the proxy data resembles noise, and even perfect reconstruction from data leakage attacks would invert the decoded gradients into unrecognizable noise, enhancing privacy. We show that TOFU enables learning with less than 1% and 7% accuracy drops on MNIST and on CIFAR-10 datasets, respectively. This drop can be recovered via a few rounds of expensive encrypted gradient exchange. This enables us to learn to near-full accuracy in a federated setup, while being 4x and 6.6x more communication efficient than the standard Federated Averaging algorithm on MNIST and CIFAR-10, respectively.
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。
