Confidential Federated Computations

arXiv:2404.10764v1 Announce Type: new
Abstract: Federated Learning and Analytics (FLA) have seen widespread adoption by technology platforms for processing sensitive on-device data. However, basic FLA systems have privacy limitations: they do not necessarily require anonymization mechanisms like differential privacy (DP), and provide limited protections against a potentially malicious service provider. Adding DP to a basic FLA system currently requires either adding excessive noise to each device's updates, or assuming an honest service provider that correctly implements the mechanism and only …

adoption analytics anonymization arxiv basic confidential cs.cr cs.lg data device differential privacy federated federated learning limitations malicious platforms privacy sensitive service service provider system systems technology