Enhancing Federated Learning with Adaptive Differential Privacy and Priority-Based Aggregation

arXiv:2406.18491v1 Announce Type: cross
Abstract: Federated learning (FL), a novel branch of distributed machine learning (ML), develops global models through a private procedure without direct access to local datasets. However, it is still possible to access the model updates (gradient updates of deep neural networks) transferred between clients and servers, potentially revealing sensitive local information to adversaries using model inversion attacks. Differential privacy (DP) offers a promising approach to addressing this issue by adding noise to the parameters. On the …

access aggregation arxiv clients cs.cr cs.dc cs.lg datasets differential privacy distributed federated federated learning global local machine machine learning networks neural networks novel privacy private procedure servers updates