Local Model Reconstruction Attacks in Federated Learning and their Uses. (arXiv:2210.16205v1 [cs.LG])

In this paper, we initiate the study of local model reconstruction attacks
for federated learning, where a honest-but-curious adversary eavesdrops the
messages exchanged between a targeted client and the server, and then
reconstructs the local/personalized model of the victim. The local model
reconstruction attack allows the adversary to trigger other classical attacks
in a more effective way, since the local model only depends on the client's
data and can leak more private information than the global model learned by the …

attacks federated learning local