mlsanityData to 14 Oct 2026

PCDM: A Diffusion-Based Data Poisoning Attack Against Federated Learning Systems

arXiv 2605.16098 ↗First posted 15 May 2026cs.CR cs.DCcited by 0

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

Abstract (arXiv)

Federated learning (FL) is vulnerable to data poisoning attacks due to its distributed nature. Although recent GAN-based data poisoning methods have indicated the potential of using generative AI to generate seemingly legitimate poisoned data, the inherent consistency of GAN outputs can still reveal a sign of data poisoning. In this paper, we propose a diffusion-based data poisoning framework against FL systems, which leverages a Poisoning-Oriented Conditional Diffusion Model (PCDM) to enable fine-grained control over the local generation of poisoned data while ensuring both attack effectiveness and stealthiness. Our PCDM incorporates an adjustable poisoning vector within the global context to precisely control the generation of poisoned data, with theoretical guarantees on attack performance. Furthermore, it employs a novel jumping diffusion strategy for lightweight and efficient poisoned data generation. We conduct the most systematic and broad experimental evaluation for FL poisoning attacks against various defenses, including advanced Byzantine robust aggregation mechanisms, on four open datasets: MNIST, Fashion-MNIST, CIFAR-10, CIFAR-100, and a real-world wireless-specific dataset VRAI. Our results demonstrate that PCDM is less likely to exhibit statistical anomalies compared with the state-of-the-art methods while more effectively degrading global FL performance, which poses a significant risk to data security in FL.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 27 of its 54 references that are in the map. First posted on arXiv 15 May 2026.

Builds on

27 of 54 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Data Poisoning and Leakage Analysis in Federated Learning19 Sep
  2. 2024Visualizing the Shadows: Unveiling Data Poisoning Behaviors in Federated Learning26 May
  3. 2024Federated Learning Under Attack: Exposing Vulnerabilities through Data Poisoning Attacks in Computer Networks5 Mar

Other references · 24

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  4. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,114
  5. 2022Diffusion Models in Vision: A Surveycited by 1,015
  6. 2018How To Backdoor Federated Learningcited by 765
  7. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 275
  8. 2022A Survey on Generative Diffusion Modelcited by 240
  9. 2021Federated Multi-Task Learning under a Mixture of Distributionscited by 192
  10. 2021Pros and Cons of GAN Evaluation Measures: New Developmentscited by 123
  11. 2022Vertical Federated Learning: Concepts, Advances and Challengescited by 108
  12. 2021Deep Generative Models in Engineering Design: A Reviewcited by 105
12 more
  1. 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 84
  2. 2023Recent Advances on Federated Learning: A Systematic Surveycited by 41
  3. 2023Advancements in Generative AI: A Comprehensive Review of GANs, GPT, Autoencoders, Diffusion Model, and Transformerscited by 36
  4. 2022LoMar: A Local Defense Against Poisoning Attack on Federated Learningcited by 31
  5. 2021Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filteringcited by 30
  6. 2022GAN-generated Faces Detection: A Survey and New Perspectivescited by 30
  7. 2019Vehicle Re-identification in Aerial Imagery: Dataset and Approachcited by 25
  8. 2022Block Hunter: Federated Learning for Cyber Threat Hunting in Blockchain-based IIoT Networkscited by 16
  9. 2024Threats and Defenses in Federated Learning Life Cycle: A Comprehensive Survey and Challengescited by 15
  10. 2024Achieving Byzantine-Resilient Federated Learning via Layer-Adaptive Sparsified Model Aggregationcited by 15
  11. 2023FLTracer: Accurate Poisoning Attack Provenance in Federated Learningcited by 8
  12. 2018Analysis of adversarial attacks against CNN-based image forgery detectorscited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024A Model Consistency-Based Countermeasure to GAN-Based Data Poisoning Attack in Federated Learning
  2. 2024Precision Guided Approach to Mitigate Data Poisoning Attacks in Federated Learning
  3. 2025SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning
  4. 2025Gradient Purification: Defense Against Poisoning Attack in Decentralized Federated Learning
  5. 2024Defending against Data Poisoning Attacks in Federated Learning via User Elimination
  6. 2025DROP: Poison Dilution via Knowledge Distillation for Federated Learning
  7. 2024A GAN-based data poisoning framework against anomaly detection in vertical federated learning
  8. 2023FreqFed: A Frequency Analysis-Based Approach for Mitigating Poisoning Attacks in Federated Learning