Google Research

Learning to Generate Image Embeddings with User-level Differential Privacy

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2023) (to appear)


We consider training feature extractors with user-level differential privacy to map images to embeddings from large-scale supervised data. To achieve user-level differential privacy, federated learning algorithms are extended and applied to aggregate user partitioned data, together with sensitivity control and noise addition. We demonstrate a variant of federated learning algorithm with partial aggregation and private reconstruction can achieve strong privacy utility trade-offs. When a large scale dataset is provided, it is possible to train feature extractors with both strong utility and privacy guarantees by combining techniques such as public pretraining, virtual clients, and partial aggregation.

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work