FedSumUp: User-Auditable Privacy-Aware Representation Sharing for Resource-Constrained Federated Intelligence
FedSumUp shares compact client representations to cut federated privacy leakage and client compute.
2 stories, newest first · one card per story
FedSumUp shares compact client representations to cut federated privacy leakage and client compute.
Researchers show colluding nodes in decentralized federated learning can reconstruct private updates despite secure aggregation, using lattice-based attacks tied to the Hidden Subset Sum Problem.
Today 1.6K readers · 2.5K views · 780 reads · all time 189K views