An adaptive federated-learning backdoor attack uses membership-inference feedback on the global model to keep malicious updates statistically similar to benign ones, evading nine robust aggregation defenses in two image datasets.
Byzantine- Robust Distributed Learning: Towards Optimal Statistical Rates,
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
-
Stealth by Conformity: Evading Robust Aggregation through Adaptive Poisoning
An adaptive federated-learning backdoor attack uses membership-inference feedback on the global model to keep malicious updates statistically similar to benign ones, evading nine robust aggregation defenses in two image datasets.