A sybil-based attack that generates virtual poisoned images by gradient matching flips a target class to a chosen label in federated learning, with the paper reporting better main-task accuracy than two gradient-matching baselines.
Bert: Pre-training of deep bidirectional transformers for language understanding,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Sybil-based Virtual Data Poisoning Attacks in Federated Learning
A sybil-based attack that generates virtual poisoned images by gradient matching flips a target class to a chosen label in federated learning, with the paper reporting better main-task accuracy than two gradient-matching baselines.