Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Xueqing, Zhang, Junkai, Chow, Ka-Ho, Chen, Juntao, Mao, Ying, Rahouti, Mohamed, Li, Xiang, Liu, Yuchen, Wei, Wenqi
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2405.16707
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929359463383040
author Zhang, Xueqing
Zhang, Junkai
Chow, Ka-Ho
Chen, Juntao
Mao, Ying
Rahouti, Mohamed
Li, Xiang
Liu, Yuchen
Wei, Wenqi
author_facet Zhang, Xueqing
Zhang, Junkai
Chow, Ka-Ho
Chen, Juntao
Mao, Ying
Rahouti, Mohamed
Li, Xiang
Liu, Yuchen
Wei, Wenqi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_16707
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Visualizing the Shadows: Unveiling Data Poisoning Behaviors in Federated Learning
Zhang, Xueqing
Zhang, Junkai
Chow, Ka-Ho
Chen, Juntao
Mao, Ying
Rahouti, Mohamed
Li, Xiang
Liu, Yuchen
Wei, Wenqi
Cryptography and Security
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.
title Visualizing the Shadows: Unveiling Data Poisoning Behaviors in Federated Learning
topic Cryptography and Security
url https://arxiv.org/abs/2405.16707