mlsanityData to 14 Oct 2026

Visualizing the Shadows: Unveiling Data Poisoning Behaviors in Federated Learning

arXiv 2405.16707 ↗First posted 26 May 2024cs.CRcited by 1

On the map: LLM safety and security → Federated unlearning and poisoning

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 5 of its 10 references that are in the map. First posted on arXiv 26 May 2024.

Builds on

5 of 10 references.

References · 5

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2018Spectral Signatures in Backdoor Attackscited by 484
  3. 2017Certified Defenses for Data Poisoning Attackscited by 303
  4. 2021SPECTRE: Defending Against Backdoor Attacks Using Robust Statisticscited by 130
  5. 2024Robust Federated Contrastive Recommender System against Model Poisoning Attackcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026PCDM: A Diffusion-Based Data Poisoning Attack Against Federated Learning Systemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Federated Learning Under Attack: Exposing Vulnerabilities through Data Poisoning Attacks in Computer Networks
  2. 2025SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning
  3. 2023A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspective
  4. 2024Precision Guided Approach to Mitigate Data Poisoning Attacks in Federated Learning
  5. 2024Data Poisoning and Leakage Analysis in Federated Learning
  6. 2024Fake or Compromised? Making Sense of Malicious Clients in Federated Learning
  7. 2025FedNIA: Noise-Induced Activation Analysis for Mitigating Data Poisoning in Federated Learning
  8. 2023FreqFed: A Frequency Analysis-Based Approach for Mitigating Poisoning Attacks in Federated Learning