Visualizing the Shadows: Unveiling Data Poisoning Behaviors in Federated Learning

TL;DR

This paper introduces a visualization system for detecting and understanding data poisoning attacks in Federated Learning, highlighting vulnerabilities and providing insights to improve system robustness.

Contribution

A novel visualization framework that simulates, analyzes, and mitigates targeted data poisoning attacks in Federated Learning systems.

Findings

Label manipulation significantly impacts model accuracy

Attack timing influences attack success

Malicious attack availability varies with attack strategies

Abstract

This demo paper examines the susceptibility of Federated Learning (FL) systems to targeted data poisoning attacks, presenting a novel system for visualizing and mitigating such threats. We simulate targeted data poisoning attacks via label flipping and analyze the impact on model performance, employing a five-component system that includes Simulation and Data Generation, Data Collection and Upload, User-friendly Interface, Analysis and Insight, and Advisory System. Observations from three demo modules: label manipulation, attack timing, and malicious attack availability, and two analysis components: utility and analytical behavior of local model updates highlight the risks to system integrity and offer insight into the resilience of FL systems. The demo is available at https://github.com/CathyXueqingZhang/DataPoisoningVis.