PDFed: Privacy-Preserving and Decentralized Asynchronous Federated Learning for Diffusion Models
On the map: Diffusion models → Robustness, privacy and adversarial aspects
Abstract (arXiv)
We present PDFed, a decentralized, aggregator-free, and asynchronous federated learning protocol for training image diffusion models using a public blockchain. In general, diffusion models are prone to memorization of training data, raising privacy and ethical concerns (e.g., regurgitation of private training data in generated images). Federated learning (FL) offers a partial solution via collaborative model training across distributed nodes that safeguard local data privacy. PDFed proposes a novel sample-based score that measures the novelty and quality of generated samples, incorporating these into a blockchain-based federated learning protocol that we show reduces private data memorization in the collaboratively trained model. In addition, PDFed enables asynchronous collaboration among participants with varying hardware capabilities, facilitating broader participation. The protocol records the provenance of AI models, improving transparency and auditability, while also considering automated incentive and reward mechanisms for participants. PDFed aims to empower artists and creators by protecting the privacy of creative works and enabling decentralized, peer-to-peer collaboration. The protocol positively impacts the creative economy by opening up novel revenue streams and fostering innovative ways for artists to benefit from their contributions to the AI space.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 14 of its 27 references that are in the map. First posted on arXiv 26 Sep 2024.
Builds on
14 of 27 references.
Closest ancestors · 2
Same direction, newest first
- 2023Federated Learning with Diffusion Models for Privacy-Sensitive Vision Tasks28 Nov
- 2023Exploring One-shot Semi-supervised Federated Learning with A Pre-trained Diffusion Model6 May
Other references · 12
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
- 2023Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion modelscited by 199
- 2021How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Modelscited by 193
- 2015Particular object retrieval with integral max-pooling of CNN activationscited by 160
- 2019Do We Train on Test Data? Purging CIFAR of Near-Duplicatescited by 61
- 2020A Non-Parametric Test to Detect Data-Copying in Generative Modelscited by 52
- 2019BAFFLE : Blockchain Based Aggregator Free Federated Learningcited by 38
- 2020BlockFLow: An Accountable and Privacy-Preserving Solution for Federated Learningcited by 12
- 2019ARCHANGEL: Tamper-proofing Video Archives using Temporal Content Hashes on the Blockchaincited by 7
- 2023DECORAIT -- DECentralized Opt-in/out Registry for AI Trainingcited by 7
- 2021Federated Learning using Smart Contracts on Blockchains, based on Reward Driven Approachcited by 2
Built on by
Citing papers per year: 2025: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025Personalized Federated Training of Diffusion Models with Privacy Guarantees
- 2024Training Diffusion Models with Federated Learning
- 2024Federated Learning Nodes Can Reconstruct Peers' Image Data
- 2024Gradient Inversion of Federated Diffusion Models
- 2024Enhancing Privacy in ControlNet and Stable Diffusion via Split Learning
- 2026FedOT: Ownership Verification and Leakage Tracing via Watermarks for Federated LDMs
- 2024Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk
- 2023Differentially Private Diffusion Models Generate Useful Synthetic Images