paper-with-me

Papers

Federated Learning in Adversarial Settings

2020-10-15 · Raouf Kerkouche, Gergely Ács, Claude Castelluccia

Federated Learning enables entities to collaboratively learn a shared prediction model while keeping their training data locally. It prevents data collection and aggregation and, therefore, mitigates the associated privacy risks. However, it still remains vulnerable to various security attacks where malicious participants aim at degrading the generated model, inserting backdoors, or inferring other participants' training data. This paper presents a new federated learning scheme that provides different trade-offs between robustness, privacy, bandwidth efficiency, and model accuracy. Our scheme uses biased quantization of model updates and hence is bandwidth efficient. It is also robust against state-of-the-art backdoor as well as model degradation attacks even when a large proportion of the participant nodes are malicious. We propose a practical differentially private extension of this scheme which protects the whole dataset of participating entities. We show that this extension performs as efficiently as the non-private but robust scheme, even with stringent privacy requirements but are less robust against model degradation and backdoor attacks. This suggests a possible fundamental trade-off between Differential Privacy and robustness.

📄 PDF Abstract BibTeX arXiv:2010.07808

Code (0)

등록된 구현이 없습니다.

Tasks

Federated LearningQuantization

Similar Papers 제목 키워드 기반

Delving into the Adversarial Robustness of Federated Learning

2023-02-19 · Jie Zhang, Bo Li, Chen Chen, Lingjuan Lyu 외

In Federated Learning (FL), models are as fragile as centrally trained models against adversarial examples. However, the adversarial robustness of federated learning remains largely unexplored. This paper casts light on …

Adversarial RobustnessFederated Learning

FAT: Federated Adversarial Training

2020-12-03 · Giulio Zizzo, Ambrish Rawat, Mathieu Sinn, Beat Buesser

Federated learning (FL) is one of the most important paradigms addressing privacy and data governance issues in machine learning (ML). Adversarial training has emerged, so far, as the most promising approach against evas…

Adversarial RobustnessFederated Learning

Ensemble Federated Adversarial Training with Non-IID data

2021-10-26 · Shuang Luo, Didi Zhu, Zexi Li, Chao Wu

Despite federated learning endows distributed clients with a cooperative training mode under the premise of protecting data privacy and security, the clients are still vulnerable when encountering adversarial samples due…

DiversityFederated Learning

Fed-Safe: Securing Federated Learning in Healthcare Against Adversarial Attacks

2023-10-12 · Erfan Darzi, Nanna M. Sijtsema, P. M. A van Ooijen

This paper explores the security aspects of federated learning applications in medical image analysis. Current robustness-oriented methods like adversarial training, secure aggregation, and homomorphic encryption often r…

Federated LearningMedical Image Analysis

The Hidden Adversarial Vulnerabilities of Medical Federated Learning

2023-10-21 · Erfan Darzi, Florian Dubost, Nanna. M. Sijtsema, P. M. A van Ooijen

In this paper, we delve into the susceptibility of federated medical image analysis systems to adversarial attacks. Our analysis uncovers a novel exploitation avenue: using gradient information from prior global model up…

Federated LearningMedical Image Analysis