# Lossless Privacy-Preserving Aggregation for Decentralized Federated Learning

arXiv: https://arxiv.org/abs/2501.04409 · HTML: https://mlsanity.com/paper/2501.04409/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 44 references that are in the map.
- First posted on arXiv 8 Jan 2025.

## Builds on (most cited first, 18 of 18)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Federated Learning with Differential Privacy: Algorithms and Performance Analysis](https://mlsanity.com/paper/1911.00222/) (2019)
- [Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent](https://mlsanity.com/paper/1705.09056/) (2017)
- [From Distributed Machine Learning to Federated Learning: A Survey](https://mlsanity.com/paper/2104.14362/) (2021)
- [LDP-FL: Practical Private Aggregation in Federated Learning with Local Differential Privacy](https://mlsanity.com/paper/2007.15789/) (2020)
- [Push-Pull Gradient Methods for Distributed Optimization in Networks](https://mlsanity.com/paper/1810.06653/) (2018)
- [Improving the Model Consistency of Decentralized Federated Learning](https://mlsanity.com/paper/2302.04083/) (2023)
- [BEER: Fast O(1/T) Rate for Decentralized Nonconvex Optimization with Communication Compression](https://mlsanity.com/paper/2201.13320/) (2022)
- [FL-WBC: Enhancing Robustness against Model Poisoning Attacks in Federated Learning from a Client Perspective](https://mlsanity.com/paper/2110.13864/) (2021)
- [Decentralized Gossip-Based Stochastic Bilevel Optimization over Communication Networks](https://mlsanity.com/paper/2206.10870/) (2022)
- [Interaction-level Membership Inference Attack Against Federated Recommender Systems](https://mlsanity.com/paper/2301.10964/) (2023)
- [Decentralized Wireless Federated Learning with Differential Privacy](https://mlsanity.com/paper/2109.09142/) (2021)
- [Revealing and Protecting Labels in Distributed Training](https://mlsanity.com/paper/2111.00556/) (2021)
- [Decentralized Stochastic Optimization with Inherent Privacy Protection](https://mlsanity.com/paper/2205.03884/) (2022)
- [Decentralized Collaborative Learning with Adaptive Reference Data for On-Device POI Recommendation](https://mlsanity.com/paper/2401.13448/) (2024)
- [Local Differential Privacy Meets Computational Social Choice -- Resilience under Voter Deletion](https://mlsanity.com/paper/2205.00771/) (2022)

## Abstract (arXiv)

Privacy concerns arise as sensitive data proliferate. Despite decentralized federated learning (DFL) aggregating gradients from neighbors to avoid direct data transmission, it still poses indirect data leaks from the transmitted gradients. Existing privacy-preserving methods for DFL add noise to gradients. They either diminish the model predictive accuracy or suffer from ineffective gradient protection. In this paper, we propose a novel lossless privacy-preserving aggregation rule named LPPA to enhance gradient protection as much as possible but without loss of DFL model predictive accuracy. LPPA subtly injects the noise difference between the sent and received noise into transmitted gradients for gradient protection. The noise difference incorporates neighbors' randomness for each client, effectively safeguarding against data leaks. LPPA employs the noise flow conservation theory to ensure that the noise impact can be globally eliminated. The global sum of all noise differences remains zero, ensuring that accurate gradient aggregation is unaffected and the model accuracy remains intact. We theoretically prove that the privacy-preserving capacity of LPPA is √2 times greater than that of noise addition, while maintaining comparable model accuracy to the standard DFL aggregation without noise injection. Experimental results verify the theoretical findings and show that LPPA achieves a 14% mean improvement in accuracy over noise addition. We also demonstrate the effectiveness of LPPA in protecting raw data and guaranteeing lossless model accuracy.