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.
Imperceptible backdoor attack: From input space to feature representation,
1 Pith paper cite this work, alongside 34 external citations. Polarity classification is still indexing.
1
Pith paper citing it
34
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 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.