Publication Date
Fall 2024
Degree Type
Master's Project
Degree Name
Master of Science in Computer Science (MSCS)
Department
Computer Science
First Advisor
Mark Stamp
Second Advisor
Katerina Potika
Third Advisor
Mike Wu
Keywords
Adversarial Attacks, Federated Learning
Abstract
In this paper, we experimentally analyze the susceptibility of selected Federated Learning (FL) systems to the presence of adversarial clients. We find that temporal attacks significantly affect model performance in FL, especially when the adversaries are active throughout and during the ending rounds of the FL process. Machine Learning models like Multinominal Logistic Regression, Support Vector Classifier (SVC), Neural Network models like Multilayer Perceptron (MLP), Convolution Neural Network (CNN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM) and tree-based machine learning models like Random Forest and XGBoost were considered. These results highlight the effectiveness of temporal attacks and the need to develop strategies to make the FL process more robust. We also explore defense mechanisms, including outlier detection in the aggregation algorithm.
Recommended Citation
Mapakshi, Rohit, "An Empirical Analysis of Adversarial Attacks in Federated Learning" (2024). Master's Projects. 1422.
https://scholarworks.sjsu.edu/etd_projects/1422
