FedCAP: Robust Federated Learning via Customized Aggregation and Personalization
- URL: http://arxiv.org/abs/2410.13083v1
- Date: Wed, 16 Oct 2024 23:01:22 GMT
- Title: FedCAP: Robust Federated Learning via Customized Aggregation and Personalization
- Authors: Youpeng Li, Xinda Wang, Fuxun Yu, Lichao Sun, Wenbin Zhang, Xuyu Wang,
- Abstract summary: Federated learning (FL) has been applied to various privacy-preserving scenarios.
We propose FedCAP, a robust FL framework against both data heterogeneity and Byzantine attacks.
We show that FedCAP performs well in several non-IID settings and shows strong robustness under a series of poisoning attacks.
- Score: 13.17735010891312
- License:
- Abstract: Federated learning (FL), an emerging distributed machine learning paradigm, has been applied to various privacy-preserving scenarios. However, due to its distributed nature, FL faces two key issues: the non-independent and identical distribution (non-IID) of user data and vulnerability to Byzantine threats. To address these challenges, in this paper, we propose FedCAP, a robust FL framework against both data heterogeneity and Byzantine attacks. The core of FedCAP is a model update calibration mechanism to help a server capture the differences in the direction and magnitude of model updates among clients. Furthermore, we design a customized model aggregation rule that facilitates collaborative training among similar clients while accelerating the model deterioration of malicious clients. With a Euclidean norm-based anomaly detection mechanism, the server can quickly identify and permanently remove malicious clients. Moreover, the impact of data heterogeneity and Byzantine attacks can be further mitigated through personalization on the client side. We conduct extensive experiments, comparing multiple state-of-the-art baselines, to demonstrate that FedCAP performs well in several non-IID settings and shows strong robustness under a series of poisoning attacks.
Related papers
- FedCLEAN: byzantine defense by CLustering Errors of Activation maps in Non-IID federated learning environments [2.5490583414858836]
Federated Learning (FL) enables clients to collaboratively train a global model using their local datasets while reinforcing data privacy.
Existing defense mechanisms assume that clients' data are independent and identically distributed (IID), making them ineffective in real-world applications where data are non-IID.
This paper presents FedCLEAN, the first defense capable of filtering attackers' model updates in a non-IID FL environment.
arXiv Detail & Related papers (2025-01-21T13:37:28Z) - Rethinking Byzantine Robustness in Federated Recommendation from Sparse Aggregation Perspective [65.65471972217814]
federated recommendation (FR) based on federated learning (FL) emerges, keeping the personal data on the local client and updating a model collaboratively.
FR has a unique sparse aggregation mechanism, where the embedding of each item is updated by only partial clients, instead of full clients in a dense aggregation of general FL.
In this paper, we reformulate the Byzantine robustness under sparse aggregation by defining the aggregation for a single item as the smallest execution unit.
We propose a family of effective attack strategies, named Spattack, which exploit the vulnerability in sparse aggregation and are categorized along the adversary's knowledge and capability.
arXiv Detail & Related papers (2025-01-06T15:19:26Z) - Robust Federated Learning in the Face of Covariate Shift: A Magnitude Pruning with Hybrid Regularization Framework for Enhanced Model Aggregation [1.519321208145928]
Federated Learning (FL) offers a promising framework for individuals aiming to collaboratively develop a shared model.
variations in data distribution among clients can profoundly affect FL methodologies, primarily due to instabilities in the aggregation process.
We propose a novel FL framework, combining individual parameter pruning and regularization techniques to improve the robustness of individual clients' models to aggregate.
arXiv Detail & Related papers (2024-12-19T16:22:37Z) - Formal Logic-guided Robust Federated Learning against Poisoning Attacks [6.997975378492098]
Federated Learning (FL) offers a promising solution to the privacy concerns associated with centralized Machine Learning (ML)
FL is vulnerable to various security threats, including poisoning attacks, where adversarial clients manipulate the training data or model updates to degrade overall model performance.
We present a defense mechanism designed to mitigate poisoning attacks in federated learning for time-series tasks.
arXiv Detail & Related papers (2024-11-05T16:23:19Z) - Certifiably Byzantine-Robust Federated Conformal Prediction [49.23374238798428]
We introduce a novel framework Rob-FCP, which executes robust federated conformal prediction effectively countering malicious clients.
We empirically demonstrate the robustness of Rob-FCP against diverse proportions of malicious clients under a variety of Byzantine attacks.
arXiv Detail & Related papers (2024-06-04T04:43:30Z) - Personalized Federated Learning with Attention-based Client Selection [57.71009302168411]
We propose FedACS, a new PFL algorithm with an Attention-based Client Selection mechanism.
FedACS integrates an attention mechanism to enhance collaboration among clients with similar data distributions.
Experiments on CIFAR10 and FMNIST validate FedACS's superiority.
arXiv Detail & Related papers (2023-12-23T03:31:46Z) - Client-side Gradient Inversion Against Federated Learning from Poisoning [59.74484221875662]
Federated Learning (FL) enables distributed participants to train a global model without sharing data directly to a central server.
Recent studies have revealed that FL is vulnerable to gradient inversion attack (GIA), which aims to reconstruct the original training samples.
We propose Client-side poisoning Gradient Inversion (CGI), which is a novel attack method that can be launched from clients.
arXiv Detail & Related papers (2023-09-14T03:48:27Z) - Mitigating Cross-client GANs-based Attack in Federated Learning [78.06700142712353]
Multi distributed multimedia clients can resort to federated learning (FL) to jointly learn a global shared model.
FL suffers from the cross-client generative adversarial networks (GANs)-based (C-GANs) attack.
We propose Fed-EDKD technique to improve the current popular FL schemes to resist C-GANs attack.
arXiv Detail & Related papers (2023-07-25T08:15:55Z) - A Secure Federated Learning Framework for Residential Short Term Load
Forecasting [1.1254693939127909]
Federated Learning (FL) is a machine learning alternative which enables collaborative learning of a model without exposing private raw data for short term load forecasting.
Standard FL is still vulnerable to an intractable cyber threat known as Byzantine attack carried out by faulty and/or malicious clients.
We develop a state-of-the-art differentially private secured FL-based framework that ensures the privacy of the individual smart meter's data while protect the security of FL models and architecture.
arXiv Detail & Related papers (2022-09-29T04:36:16Z) - Robust Quantity-Aware Aggregation for Federated Learning [72.59915691824624]
Malicious clients can poison model updates and claim large quantities to amplify the impact of their model updates in the model aggregation.
Existing defense methods for FL, while all handling malicious model updates, either treat all quantities benign or simply ignore/truncate the quantities of all clients.
We propose a robust quantity-aware aggregation algorithm for federated learning, called FedRA, to perform the aggregation with awareness of local data quantities.
arXiv Detail & Related papers (2022-05-22T15:13:23Z) - Byzantine-robust Federated Learning through Spatial-temporal Analysis of
Local Model Updates [6.758334200305236]
Federated Learning (FL) enables multiple distributed clients (e.g., mobile devices) to collaboratively train a centralized model while keeping the training data locally on the client.
In this paper, we propose to mitigate these failures and attacks from a spatial-temporal perspective.
Specifically, we use a clustering-based method to detect and exclude incorrect updates by leveraging their geometric properties in the parameter space.
arXiv Detail & Related papers (2021-07-03T18:48:11Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.