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.
@article{arxiv.2405.16707,
title = {Visualizing the Shadows: Unveiling Data Poisoning Behaviors in Federated Learning},
author = {Xueqing Zhang and Junkai Zhang and Ka-Ho Chow and Juntao Chen and Ying Mao and Mohamed Rahouti and Xiang Li and Yuchen Liu and Wenqi Wei},
journal= {arXiv preprint arXiv:2405.16707},
year = {2024}
}