paper-with-me

홈 › Papers

FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks

2025-08-26 · Enrique Mármol Campos, Aurora González Vidal, José Luis Hernández Ramos, Antonio Skarmeta arxiv

Federated Learning (FL) has become a powerful technique for training Machine Learning (ML) models in a decentralized manner, preserving the privacy of the training datasets involved. However, the decentralized nature of FL limits the visibility of the training process, relying heavily on the honesty of participating clients. This assumption opens the door to malicious third parties, known as Byzantine clients, which can poison the training process by submitting false model updates. Such malicious clients may engage in poisoning attacks, manipulating either the dataset or the model parameters to induce misclassification. In response, this study introduces FLAegis, a two-stage defensive framework designed to identify Byzantine clients and improve the robustness of FL systems. Our approach leverages symbolic time series transformation (SAX) to amplify the differences between benign and malicious models, and spectral clustering, which enables accurate detection of adversarial behavior. Furthermore, we incorporate a robust FFT-based aggregation function as a final layer to mitigate the impact of those Byzantine clients that manage to evade prior defenses. We rigorously evaluate our method against five poisoning attacks, ranging from simple label flipping to adaptive optimization-based strategies. Notably, our approach outperforms state-of-the-art defenses in both detection precision and final model accuracy, maintaining consistently high performance even under strong adversarial conditions.

📄 PDF Abstract BibTeX arXiv:2508.18737

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

Resilient Federated Chain: Transforming Blockchain Consensus into an Active Defense Layer for Federated Learning

2026-02-25 · Mario García-Márquez, Nuria Rodríguez-Barroso, M. Victoria Luzón, Francisco Herrera arxiv

Federated Learning (FL) has emerged as a key paradigm for building Trustworthy AI systems by enabling privacy-preserving, decentralized model training. However, FL is highly susceptible to adversarial attacks that compro…

Image ClassificationFederated Learning

Celtibero: Robust Layered Aggregation for Federated Learning

2024-08-26 · Borja Molina-Coronado

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 …

Federated Learning

Hammer and Anvil: Toward a Theory of Backdoors in Federated Learning

2025-09-09 · Lucas Fenaux, Zheng Wang, Jacob Yan, Nathan Chung 외 arxiv

Federated Learning (FL) enables distributed model training but is vulnerable to backdoor attacks, where malicious clients embed attacker-controlled behaviors into the global model. Existing defenses fail against adaptive…

Federated LearningOutlier Detection

FL-PLAS: Federated Learning with Partial Layer Aggregation for Backdoor Defense Against High-Ratio Malicious Clients

2025-05-17 · Jianyi Zhang, Ziyin Zhou, Yilong Li, Qichao Jin

Federated learning (FL) is gaining increasing attention as an emerging collaborative machine learning approach, particularly in the context of large-scale computing and data systems. However, the fundamental algorithm of…

backdoor defenseFederated Learning

A Novel Defense Against Poisoning Attacks on Federated Learning: LayerCAM Augmented with Autoencoder

2024-06-02 · Jingjing Zheng, Xin Yuan, Kai Li, Wei Ni 외

Recent attacks on federated learning (FL) can introduce malicious model updates that circumvent widely adopted Euclidean distance-based detection methods. This paper proposes a novel defense strategy, referred to as Laye…

Federated LearningModel Poisoning