paper-with-me

홈 › Papers

LoMar: A Local Defense Against Poisoning Attack on Federated Learning

2022-01-08 · Xingyu Li, Zhe Qu, Shangqing Zhao, Bo Tang, Zhuo Lu, Yao Liu

Federated learning (FL) provides a high efficient decentralized machine learning framework, where the training data remains distributed at remote clients in a network. Though FL enables a privacy-preserving mobile edge computing framework using IoT devices, recent studies have shown that this approach is susceptible to poisoning attacks from the side of remote clients. To address the poisoning attacks on FL, we provide a \textit{two-phase} defense algorithm called {Lo}cal {Ma}licious Facto{r} (LoMar). In phase I, LoMar scores model updates from each remote client by measuring the relative distribution over their neighbors using a kernel density estimation method. In phase II, an optimal threshold is approximated to distinguish malicious and clean updates from a statistical perspective. Comprehensive experiments on four real-world datasets have been conducted, and the experimental results show that our defense strategy can effectively protect the FL system. {Specifically, the defense performance on Amazon dataset under a label-flipping attack indicates that, compared with FG+Krum, LoMar increases the target label testing accuracy from $96.0\%$ to $98.8\%$, and the overall averaged testing accuracy from $90.1\%$ to $97.0\%$.

📄 PDF Abstract BibTeX arXiv:2201.02873

Code (0)

등록된 구현이 없습니다.

Tasks

Density EstimationEdge-computingFederated LearningPrivacy Preserving

Similar Papers 제목 키워드 기반

Local Model Poisoning Attacks to Byzantine-Robust Federated Learning

2019-11-26 · Minghong Fang, Xiaoyu Cao, Jinyuan Jia, Neil Zhenqiang Gong

In federated learning, multiple client devices jointly learn a machine learning model: each client device maintains a local model for its local training dataset, while a master device maintains a global model via aggrega…

BIG-bench Machine LearningData PoisoningFederated LearningModel Poisoning

FedMID: A Data-Free Method for Using Intermediate Outputs as a Defense Mechanism Against Poisoning Attacks in Federated Learning

2024-04-18 · Sungwon Han, Hyeonho Song, Sungwon Park, Meeyoung Cha

Federated learning combines local updates from clients to produce a global model, which is susceptible to poisoning attacks. Most previous defense strategies relied on vectors derived from projections of local updates on…

Federated Learning

Defending Against Sophisticated Poisoning Attacks with RL-based Aggregation in Federated Learning

2024-06-20 · Yujing Wang, Hainan Zhang, Sijia Wen, Wangjie Qiu 외

Federated learning is highly susceptible to model poisoning attacks, especially those meticulously crafted for servers. Traditional defense methods mainly focus on updating assessments or robust aggregation against manua…

Federated LearningModel Poisoning

Deep Partition Aggregation: Provable Defense against General Poisoning Attacks

2020-06-26 · Alexander Levine, Soheil Feizi

Adversarial poisoning attacks distort training data in order to corrupt the test-time behavior of a classifier. A provable defense provides a certificate for each test sample, which is a lower bound on the magnitude of a…

FL-WBC: Enhancing Robustness against Model Poisoning Attacks in Federated Learning from a Client Perspective

2021-10-26 · NeurIPS 2021 12 · Jingwei Sun, Ang Li, Louis DiValentin, Amin Hassanzadeh 외

Federated learning (FL) is a popular distributed learning framework that trains a global model through iterative communications between a central server and edge devices. Recent works have demonstrated that FL is vulnera…

Federated LearningModel Poisoning