Temporal Analysis of Adversarial Attacks in Federated Learning

TL;DR

This paper experimentally investigates how temporal adversarial attacks impact federated learning models, revealing their significant effect and emphasizing the need for robust defense strategies.

Contribution

It provides a comprehensive analysis of temporal attacks on various federated learning models and evaluates simple defense mechanisms.

Findings

Temporal attacks significantly degrade model performance.

Later-round adversaries are more effective.

Outlier detection can mitigate some attack effects.

Abstract

In this paper, we experimentally analyze the robustness of selected Federated Learning (FL) systems in the presence of adversarial clients. We find that temporal attacks significantly affect model performance in the FL models tested, especially when the adversaries are active throughout or during the later rounds. We consider a variety of classic learning models, including Multinominal Logistic Regression (MLR), Random Forest, XGBoost, Support Vector Classifier (SVC), as well as various Neural Network models including Multilayer Perceptron (MLP), Convolution Neural Network (CNN), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM). Our results highlight the effectiveness of temporal attacks and the need to develop strategies to make the FL process more robust against such attacks. We also briefly consider the effectiveness of defense mechanisms, including outlier detection in the aggregation algorithm.