FedMLSecurity: A Benchmark for Attacks and Defenses in Federated Learning and LLMs

by   Shanshan Han, et al.
University of California, Irvine
Lehigh University
University of Southern California
Zhejiang University
University of Illinois at Urbana-Champaign

This paper introduces FedMLSecurity, a benchmark that simulates adversarial attacks and corresponding defense mechanisms in Federated Learning (FL). As an integral module of the open-sourced library FedML that facilitates FL algorithm development and performance comparison, FedMLSecurity enhances the security assessment capacity of FedML. FedMLSecurity comprises two principal components: FedMLAttacker, which simulates attacks injected into FL training, and FedMLDefender, which emulates defensive strategies designed to mitigate the impacts of the attacks. FedMLSecurity is open-sourced 1 and is customizable to a wide range of machine learning models (e.g., Logistic Regression, ResNet, GAN, etc.) and federated optimizers (e.g., FedAVG, FedOPT, FedNOVA, etc.). Experimental evaluations in this paper also demonstrate the ease of application of FedMLSecurity to Large Language Models (LLMs), further reinforcing its versatility and practical utility in various scenarios.


page 1

page 2

page 3

page 4


Meta Federated Learning

Due to its distributed methodology alongside its privacy-preserving feat...

Federated Learning Attacks and Defenses: A Survey

In terms of artificial intelligence, there are several security and priv...

Defense Strategies Toward Model Poisoning Attacks in Federated Learning: A Survey

Advances in distributed machine learning can empower future communicatio...

Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Federated Learning

While recent works have indicated that federated learning (FL) is vulner...

Attack of the Tails: Yes, You Really Can Backdoor Federated Learning

Due to its decentralized nature, Federated Learning (FL) lends itself to...

Backdoor Federated Learning by Poisoning Backdoor-Critical Layers

Federated learning (FL) has been widely deployed to enable machine learn...

HAFLO: GPU-Based Acceleration for Federated Logistic Regression

In recent years, federated learning (FL) has been widely applied for sup...

Please sign up or login with your details

Forgot password? Click here to reset