SAPAG: A Self-Adaptive Privacy Attack From Gradients

Understand

Distributed learning such as federated learning or collaborative learning enables model training on decentralized data from users and only collects local gradients, where data is processed close to its sources for data privacy.

• The nature of not centralizing the training data addresses the privacy issue of privacy-sensitive data.
• Recent studies show that a third party can reconstruct the true training data in the distributed machine learning system through the publicly-shared gradients.
• However, existing reconstruction attack frameworks lack generalizability on different Deep Neural Network (DNN) architectures and different weight distribution initialization, and can only succeed in the early training phase.