A client-side adversarial-trigger search plus model patching reduces backdoor attack success in federated learning to near zero on MNIST and Fashion-MNIST, with the largest gains over server-side defenses in non-i.i.d. settings.
Celtibero: Robust Layered Aggregation for Federated Learning
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Federated Learning (FL) is an innovative approach to distributed machine learning. While FL offers significant privacy advantages, it also faces security challenges, particularly from poisoning attacks where adversaries deliberately manipulate local model updates to degrade model performance or introduce hidden backdoors. Existing defenses against these attacks have been shown to be effective when the data on the nodes is identically and independently distributed (i.i.d.), but they often fail under less restrictive, non-i.i.d data conditions. To overcome these limitations, we introduce Celtibero, a novel defense mechanism that integrates layered aggregation to enhance robustness against adversarial manipulation. Through extensive experiments on the MNIST and IMDB datasets, we demonstrate that Celtibero consistently achieves high main task accuracy (MTA) while maintaining minimal attack success rates (ASR) across a range of untargeted and targeted poisoning attacks. Our results highlight the superiority of Celtibero over existing defenses such as FL-Defender, LFighter, and FLAME, establishing it as a highly effective solution for securing federated learning systems against sophisticated poisoning attacks.
citation-role summary
citation-polarity summary
fields
cs.CR 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Client-Side Patching against Backdoor Attacks in Federated Learning
A client-side adversarial-trigger search plus model patching reduces backdoor attack success in federated learning to near zero on MNIST and Fashion-MNIST, with the largest gains over server-side defenses in non-i.i.d. settings.