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.

翻译：本演示论文探讨了联邦学习（FL）系统对定向数据投毒攻击的脆弱性，并提出了一种用于可视化和缓解此类威胁的新颖系统。我们通过标签翻转模拟定向数据投毒攻击，并分析其对模型性能的影响，采用了一个包含五个组件的系统：模拟与数据生成、数据收集与上传、用户友好界面、分析与洞察以及咨询系统。通过对三个演示模块（标签操纵、攻击时机和恶意攻击可用性）以及两个分析组件（本地模型更新的效用和分析行为）的观察，我们揭示了系统完整性面临的风险，并深入探讨了FL系统的鲁棒性。演示系统可在 https://github.com/CathyXueqingZhang/DataPoisoningVis 访问。