An Empirical Analysis of Federated Learning Models Subject to Label-Flipping Adversarial Attack

TL;DR

This paper empirically evaluates the robustness of various federated learning models against label-flipping adversarial attacks across different client and attack intensities, revealing model-specific vulnerabilities.

Contribution

It provides a comprehensive empirical analysis of how different federated learning models respond to label-flipping attacks, highlighting their varying robustness levels.

Findings

Models differ in robustness to adversarial client percentage.

Models vary in vulnerability to label-flipping extent.

Robustness depends on attack intensity and model type.

Abstract

In this paper, we empirically analyze adversarial attacks on selected federated learning models. The specific learning models considered are Multinominal Logistic Regression (MLR), Support Vector Classifier (SVC), Multilayer Perceptron (MLP), Convolution Neural Network (CNN), %Recurrent Neural Network (RNN), Random Forest, XGBoost, and Long Short-Term Memory (LSTM). For each model, we simulate label-flipping attacks, experimenting extensively with 10 federated clients and 100 federated clients. We vary the percentage of adversarial clients from 10% to 100% and, simultaneously, the percentage of labels flipped by each adversarial client is also varied from 10% to 100%. Among other results, we find that models differ in their inherent robustness to the two vectors in our label-flipping attack, i.e., the percentage of adversarial clients, and the percentage of labels flipped by each adversarial client. We discuss the potential practical implications of our results.