GI-SMN: Gradient Inversion Attack against Federated Learning without Prior Knowledge

arXiv:2405.03516v1 Announce Type: new
Abstract: Federated learning (FL) has emerged as a privacy-preserving machine learning approach where multiple parties share gradient information rather than original user data. Recent work has demonstrated that gradient inversion attacks can exploit the gradients of FL to recreate the original user data, posing significant privacy risks. However, these attacks make strong assumptions about the attacker, such as altering the model structure or parameters, gaining batch normalization statistics, or acquiring prior knowledge of the original training …

abstract arxiv attacks cs.lg data exploit federated learning gradient information knowledge machine machine learning multiple parties prior privacy recreate type user data work