Label-flipping and oversampling attacks on federated conditional GANs shift the generated target-class distribution toward the source class linearly in poisoning strength while only quadratically changing the true target distribution, making the attack hard to detect from aggregate metrics.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Targeted Label-Flipping and Oversampling Attacks on Federated Conditional GANs
Label-flipping and oversampling attacks on federated conditional GANs shift the generated target-class distribution toward the source class linearly in poisoning strength while only quadratically changing the true target distribution, making the attack hard to detect from aggregate metrics.