paper-with-me

홈 › Papers

RobustFed: A Truth Inference Approach for Robust Federated Learning

2021-07-18 · Farnaz Tahmasebian, Jian Lou, Li Xiong

Federated learning is a prominent framework that enables clients (e.g., mobile devices or organizations) to train a collaboratively global model under a central server's orchestration while keeping local training datasets' privacy. However, the aggregation step in federated learning is vulnerable to adversarial attacks as the central server cannot manage clients' behavior. Therefore, the global model's performance and convergence of the training process will be affected under such attacks.To mitigate this vulnerability issue, we propose a novel robust aggregation algorithm inspired by the truth inference methods in crowdsourcing via incorporating the worker's reliability into aggregation. We evaluate our solution on three real-world datasets with a variety of machine learning models. Experimental results show that our solution ensures robust federated learning and is resilient to various types of attacks, including noisy data attacks, Byzantine attacks, and label flipping attacks.

📄 PDF Abstract BibTeX arXiv:2107.08402

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

FACT or Fiction: Can Truthful Mechanisms Eliminate Federated Free Riding?

2024-05-22 · Marco Bornstein, Amrit Singh Bedi, Abdirisak Mohamed, Furong Huang

Standard federated learning (FL) approaches are vulnerable to the free-rider dilemma: participating agents can contribute little to nothing yet receive a well-trained aggregated model. While prior mechanisms attempt to s…

Federated Learning

Probabilistic Inference for Learning from Untrusted Sources

2021-01-15 · Duc Thien Nguyen, Shiau Hoong Lim, Laura Wynter, Desmond Cai

Federated learning brings potential benefits of faster learning, better solutions, and a greater propensity to transfer when heterogeneous data from different parties increases diversity. However, because federated learn…

Bayesian InferenceCollaborative FilteringDiversityFederated Learning

Knowledge-Free Correlated Agreement for Incentivizing Federated Learning

2026-05-06 · Leon Witt, Togrul Abbasli, Kentaroh Toyoda, Wojciech Samek 외 arxiv

We introduce Knowledge-Free Correlated Agreement (KFCA) to reward client contributions in federated learning (FL) without relying on ground truth, a public test set, or distribution knowledge. Under categorical reports a…

Federated Learning

On the Arithmetic and Geometric Fusion of Beliefs for Distributed Inference

2022-04-28 · Mert Kayaalp, Yunus Inan, Emre Telatar, Ali H. Sayed

We study the asymptotic learning rates under linear and log-linear combination rules of belief vectors in a distributed hypothesis testing problem. We show that under both combination strategies, agents are able to learn…

Diversity

Identifying the Truth of Global Model: A Generic Solution to Defend Against Byzantine and Backdoor Attacks in Federated Learning (full version)

2023-11-17 · Sheldon C. Ebron, Meiying Zhang, Kan Yang

Federated Learning (FL) enables multiple parties to train machine learning models collaboratively without sharing the raw training data. However, the federated nature of FL enables malicious clients to influence a traine…

Federated LearningModel Poisoning