paper-with-me

Papers

Attack-Resistant Federated Learning with Residual-based Reweighting

2019-12-24 · Shuhao Fu, Chulin Xie, Bo Li, Qifeng Chen

Federated learning has a variety of applications in multiple domains by utilizing private training data stored on different devices. However, the aggregation process in federated learning is highly vulnerable to adversarial attacks so that the global model may behave abnormally under attacks. To tackle this challenge, we present a novel aggregation algorithm with residual-based reweighting to defend federated learning. Our aggregation algorithm combines repeated median regression with the reweighting scheme in iteratively reweighted least squares. Our experiments show that our aggregation algorithm outperforms other alternative algorithms in the presence of label-flipping and backdoor attacks. We also provide theoretical analysis for our aggregation algorithm.

📄 PDF Abstract BibTeX arXiv:1912.11464

Code (2)

fushuhao6/Attack-Resistant-Federated-Learning 공식 구현 pytorch
howardmumu/Attack-Resistant-Federated-Learning pytorch

Tasks

Federated Learningregression

Similar Papers 제목 키워드 기반

ResSFL: A Resistance Transfer Framework for Defending Model Inversion Attack in Split Federated Learning

2022-05-09 · CVPR 2022 1 · Jingtao Li, Adnan Siraj Rakin, Xing Chen, Zhezhi He 외

This work aims to tackle Model Inversion (MI) attack on Split Federated Learning (SFL). SFL is a recent distributed training scheme where multiple clients send intermediate activations (i.e., feature map), instead of raw…

Federated Learning

Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregation

2022-10-13 · Zhiyuan Zhang, Qi Su, Xu sun

Despite the potential of federated learning, it is known to be vulnerable to backdoor attacks. Many robust federated aggregation methods are proposed to reduce the potential backdoor risk. However, they are mainly valida…

Federated Learning

DFedReweighting: A Unified Framework for Objective-Oriented Reweighting in Decentralized Federated Learning

2025-12-12 · Kaichuang Zhang, Wei Yin, Jinghao Yang, Ping Xu arxiv

Decentralized federated learning (DFL) has emerged as a promising paradigm that enables multiple clients to collaboratively train machine learning models through iterative rounds of local training, communication, and agg…

Federated Learning

FedGrad: Mitigating Backdoor Attacks in Federated Learning Through Local Ultimate Gradients Inspection

2023-04-29 · Thuy Dung Nguyen, Anh Duy Nguyen, Kok-Seng Wong, Huy Hieu Pham 외

Federated learning (FL) enables multiple clients to train a model without compromising sensitive data. The decentralized nature of FL makes it susceptible to adversarial attacks, especially backdoor insertion during trai…

Backdoor AttackFederated Learning

Just a Simple Transformation is Enough for Data Protection in Vertical Federated Learning

2024-12-16 · Andrei Semenov, Philip Zmushko, Alexander Pichugin, Aleksandr Beznosikov

Vertical Federated Learning (VFL) aims to enable collaborative training of deep learning models while maintaining privacy protection. However, the VFL procedure still has components that are vulnerable to attacks by mali…

Federated LearningPrivacy Preserving Deep LearningVertical Federated Learning