A malicious federated learning server can hide a secret model inside client parameters via code injection and later reconstruct the client's training images from Fibonacci-coded index queries.
Deep learning with differential privacy
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Hidden Data Privacy Breaches in Federated Learning
A malicious federated learning server can hide a secret model inside client parameters via code injection and later reconstruct the client's training images from Fibonacci-coded index queries.