Saved in:
Bibliographic Details
Main Authors: Bhatnagar, Kunal, Chattanathan, Sagana, Dang, Angela, Eranki, Bhargav, Rana, Ronnit, Sridhar, Charan, Vedam, Siddharth, Yao, Angie, Stamp, Mark
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.18507
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908886503522304
author Bhatnagar, Kunal
Chattanathan, Sagana
Dang, Angela
Eranki, Bhargav
Rana, Ronnit
Sridhar, Charan
Vedam, Siddharth
Yao, Angie
Stamp, Mark
author_facet Bhatnagar, Kunal
Chattanathan, Sagana
Dang, Angela
Eranki, Bhargav
Rana, Ronnit
Sridhar, Charan
Vedam, Siddharth
Yao, Angie
Stamp, Mark
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_18507
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle An Empirical Analysis of Federated Learning Models Subject to Label-Flipping Adversarial Attack
Bhatnagar, Kunal
Chattanathan, Sagana
Dang, Angela
Eranki, Bhargav
Rana, Ronnit
Sridhar, Charan
Vedam, Siddharth
Yao, Angie
Stamp, Mark
Machine Learning
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.
title An Empirical Analysis of Federated Learning Models Subject to Label-Flipping Adversarial Attack
topic Machine Learning
url https://arxiv.org/abs/2412.18507