Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew Resilience

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huynh, Thanh Trung, Nguyen, Trong Bang, Nguyen, Phi Le, Nguyen, Thanh Tam, Weidlich, Matthias, Nguyen, Quoc Viet Hung, Aberer, Karl
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910460982329344
author Huynh, Thanh Trung
Nguyen, Trong Bang
Nguyen, Phi Le
Nguyen, Thanh Tam
Weidlich, Matthias
Nguyen, Quoc Viet Hung
Aberer, Karl
author_facet Huynh, Thanh Trung
Nguyen, Trong Bang
Nguyen, Phi Le
Nguyen, Thanh Tam
Weidlich, Matthias
Nguyen, Quoc Viet Hung
Aberer, Karl
contents Federated learning (FL) has recently emerged as a compelling machine learning paradigm, prioritizing the protection of privacy for training data. The increasing demand to address issues such as ``the right to be forgotten'' and combat data poisoning attacks highlights the importance of techniques, known as \textit{unlearning}, which facilitate the removal of specific training data from trained FL models. Despite numerous unlearning methods proposed for centralized learning, they often prove inapplicable to FL due to fundamental differences in the operation of the two learning paradigms. Consequently, unlearning in FL remains in its early stages, presenting several challenges. Many existing unlearning solutions in FL require a costly retraining process, which can be burdensome for clients. Moreover, these methods are primarily validated through experiments, lacking theoretical assurances. In this study, we introduce Fast-FedUL, a tailored unlearning method for FL, which eliminates the need for retraining entirely. Through meticulous analysis of the target client's influence on the global model in each round, we develop an algorithm to systematically remove the impact of the target client from the trained model. In addition to presenting empirical findings, we offer a theoretical analysis delineating the upper bound of our unlearned model and the exact retrained model (the one obtained through retraining using untargeted clients). Experimental results with backdoor attack scenarios indicate that Fast-FedUL effectively removes almost all traces of the target client, while retaining the knowledge of untargeted clients (obtaining a high accuracy of up to 98\% on the main task). Significantly, Fast-FedUL attains the lowest time complexity, providing a speed that is 1000 times faster than retraining. Our source code is publicly available at \url{https://github.com/thanhtrunghuynh93/fastFedUL}.
format Preprint
id arxiv_https___arxiv_org_abs_2405_18040
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew Resilience
Huynh, Thanh Trung
Nguyen, Trong Bang
Nguyen, Phi Le
Nguyen, Thanh Tam
Weidlich, Matthias
Nguyen, Quoc Viet Hung
Aberer, Karl
Machine Learning
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
Emerging Technologies
Federated learning (FL) has recently emerged as a compelling machine learning paradigm, prioritizing the protection of privacy for training data. The increasing demand to address issues such as ``the right to be forgotten'' and combat data poisoning attacks highlights the importance of techniques, known as \textit{unlearning}, which facilitate the removal of specific training data from trained FL models. Despite numerous unlearning methods proposed for centralized learning, they often prove inapplicable to FL due to fundamental differences in the operation of the two learning paradigms. Consequently, unlearning in FL remains in its early stages, presenting several challenges. Many existing unlearning solutions in FL require a costly retraining process, which can be burdensome for clients. Moreover, these methods are primarily validated through experiments, lacking theoretical assurances. In this study, we introduce Fast-FedUL, a tailored unlearning method for FL, which eliminates the need for retraining entirely. Through meticulous analysis of the target client's influence on the global model in each round, we develop an algorithm to systematically remove the impact of the target client from the trained model. In addition to presenting empirical findings, we offer a theoretical analysis delineating the upper bound of our unlearned model and the exact retrained model (the one obtained through retraining using untargeted clients). Experimental results with backdoor attack scenarios indicate that Fast-FedUL effectively removes almost all traces of the target client, while retaining the knowledge of untargeted clients (obtaining a high accuracy of up to 98\% on the main task). Significantly, Fast-FedUL attains the lowest time complexity, providing a speed that is 1000 times faster than retraining. Our source code is publicly available at \url{https://github.com/thanhtrunghuynh93/fastFedUL}.
title Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew Resilience
topic Machine Learning
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
Emerging Technologies
url https://arxiv.org/abs/2405.18040