FedSecurity: Benchmarking Attacks and Defenses in Federated Learning and Federated LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Han, Shanshan, Buyukates, Baturalp, Hu, Zijian, Jin, Han, Jin, Weizhao, Sun, Lichao, Wang, Xiaoyang, Wu, Wenxuan, Xie, Chulin, Yao, Yuhang, Zhang, Kai, Zhang, Qifan, Zhang, Yuhui, Joe-Wong, Carlee, Avestimehr, Salman, He, Chaoyang
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911928110022656
author Han, Shanshan
Buyukates, Baturalp
Hu, Zijian
Jin, Han
Jin, Weizhao
Sun, Lichao
Wang, Xiaoyang
Wu, Wenxuan
Xie, Chulin
Yao, Yuhang
Zhang, Kai
Zhang, Qifan
Zhang, Yuhui
Joe-Wong, Carlee
Avestimehr, Salman
He, Chaoyang
author_facet Han, Shanshan
Buyukates, Baturalp
Hu, Zijian
Jin, Han
Jin, Weizhao
Sun, Lichao
Wang, Xiaoyang
Wu, Wenxuan
Xie, Chulin
Yao, Yuhang
Zhang, Kai
Zhang, Qifan
Zhang, Yuhui
Joe-Wong, Carlee
Avestimehr, Salman
He, Chaoyang
contents This paper introduces FedSecurity, an end-to-end benchmark that serves as a supplementary component of the FedML library for simulating adversarial attacks and corresponding defense mechanisms in Federated Learning (FL). FedSecurity eliminates the need for implementing the fundamental FL procedures, e.g., FL training and data loading, from scratch, thus enables users to focus on developing their own attack and defense strategies. It contains two key components, including FedAttacker that conducts a variety of attacks during FL training, and FedDefender that implements defensive mechanisms to counteract these attacks. FedSecurity has the following features: i) It offers extensive customization options to accommodate a broad range of machine learning models (e.g., Logistic Regression, ResNet, and GAN) and FL optimizers (e.g., FedAVG, FedOPT, and FedNOVA); ii) it enables exploring the effectiveness of attacks and defenses across different datasets and models; and iii) it supports flexible configuration and customization through a configuration file and some APIs. We further demonstrate FedSecurity's utility and adaptability through federated training of Large Language Models (LLMs) to showcase its potential on a wide range of complex applications.
format Preprint
id arxiv_https___arxiv_org_abs_2306_04959
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle FedSecurity: Benchmarking Attacks and Defenses in Federated Learning and Federated LLMs
Han, Shanshan
Buyukates, Baturalp
Hu, Zijian
Jin, Han
Jin, Weizhao
Sun, Lichao
Wang, Xiaoyang
Wu, Wenxuan
Xie, Chulin
Yao, Yuhang
Zhang, Kai
Zhang, Qifan
Zhang, Yuhui
Joe-Wong, Carlee
Avestimehr, Salman
He, Chaoyang
Cryptography and Security
Artificial Intelligence
This paper introduces FedSecurity, an end-to-end benchmark that serves as a supplementary component of the FedML library for simulating adversarial attacks and corresponding defense mechanisms in Federated Learning (FL). FedSecurity eliminates the need for implementing the fundamental FL procedures, e.g., FL training and data loading, from scratch, thus enables users to focus on developing their own attack and defense strategies. It contains two key components, including FedAttacker that conducts a variety of attacks during FL training, and FedDefender that implements defensive mechanisms to counteract these attacks. FedSecurity has the following features: i) It offers extensive customization options to accommodate a broad range of machine learning models (e.g., Logistic Regression, ResNet, and GAN) and FL optimizers (e.g., FedAVG, FedOPT, and FedNOVA); ii) it enables exploring the effectiveness of attacks and defenses across different datasets and models; and iii) it supports flexible configuration and customization through a configuration file and some APIs. We further demonstrate FedSecurity's utility and adaptability through federated training of Large Language Models (LLMs) to showcase its potential on a wide range of complex applications.
title FedSecurity: Benchmarking Attacks and Defenses in Federated Learning and Federated LLMs
topic Cryptography and Security
Artificial Intelligence
url https://arxiv.org/abs/2306.04959