Celtibero: Robust Layered Aggregation for Federated Learning
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningSimilar Papers 제목 키워드 기반
Fedcompass: Federated Clustered and Periodic Aggregation Framework for Hybrid Classical-Quantum Models
Federated learning enables collaborative model training across decentralized clients under privacy constraints. Quantum computing offers potential for alleviating computational and communication burdens in federated lear…
Federated LearningCompression with Exact Error Distribution for Federated Learning
Compression schemes have been extensively used in Federated Learning (FL) to reduce the communication cost of distributed learning. While most approaches rely on a bounded variance assumption of the noise produced by the…
Federated LearningAutomated Byzantine-Resilient Clustered Decentralized Federated Learning for Battery Intelligence in Connected EVs
Federated learning (FL) has emerged as a promising paradigm for managing electric vehicle (EV) battery data in intelligent transportation systems (ITS), enabling privacy-preserving tasks such as anomaly detection and cap…
Federated LearningAnomaly DetectionAdaptive Deadline and Batch Layered Synchronized Federated Learning
Federated learning (FL) enables collaborative model training across distributed edge devices while preserving data privacy, and typically operates in a round-based synchronous manner. However, synchronous FL suffers from…
Federated LearningBuffered Asynchronous Secure Aggregation for Cross-Device Federated Learning
Asynchronous federated learning (AFL) is an effective method to address the challenge of device heterogeneity in cross-device federated learning. However, AFL is usually incompatible with existing secure aggregation prot…
Federated Learning