# Provable Privacy Advantages of Decentralized Federated Learning via Distributed Optimization

arXiv: https://arxiv.org/abs/2407.09324 · HTML: https://mlsanity.com/paper/2407.09324/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 72 references that are in the map.
- First posted on arXiv 12 Jul 2024.

## Builds on (most cited first, 30 of 38)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Inverting Gradients -- How easy is it to break privacy in federated learning?](https://mlsanity.com/paper/2003.14053/) (2020)
- [Exploiting Unintended Feature Leakage in Collaborative Learning](https://mlsanity.com/paper/1805.04049/) (2018)
- [Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent](https://mlsanity.com/paper/1705.09056/) (2017)
- [iDLG: Improved Deep Leakage from Gradients](https://mlsanity.com/paper/2001.02610/) (2020)
- [A Unified Theory of Decentralized SGD with Changing Topology and Local Updates](https://mlsanity.com/paper/2003.10422/) (2020)
- [See through Gradients: Image Batch Recovery via GradInversion](https://mlsanity.com/paper/2104.07586/) (2021)
- [Systematic Evaluation of Privacy Risks of Machine Learning Models](https://mlsanity.com/paper/2003.10595/) (2020)
- [Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning](https://mlsanity.com/paper/1812.00535/) (2018)
- [The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks](https://mlsanity.com/paper/1911.07135/) (2019)
- [On the Convergence of Decentralized Gradient Descent](https://mlsanity.com/paper/1310.7063/) (2013)
- [D2: Decentralized Training over Decentralized Data](https://mlsanity.com/paper/1803.07068/) (2018)
- [When the Curious Abandon Honesty: Federated Learning Is Not Private](https://mlsanity.com/paper/2112.02918/) (2021)
- [Tightening Mutual Information Based Bounds on Generalization Error](https://mlsanity.com/paper/1901.04609/) (2019)
- [Gradient Inversion with Generative Image Prior](https://mlsanity.com/paper/2110.14962/) (2021)
- [Decentralized Federated Learning: A Segmented Gossip Approach](https://mlsanity.com/paper/1908.07782/) (2019)
- [A Framework for Evaluating Gradient Leakage Attacks in Federated Learning](https://mlsanity.com/paper/2004.10397/) (2020)
- [Differential Privacy as a Mutual Information Constraint](https://mlsanity.com/paper/1608.03677/) (2016)
- [RelaySum for Decentralized Deep Learning on Heterogeneous Data](https://mlsanity.com/paper/2110.04175/) (2021)
- [On the (In)security of Peer-to-Peer Decentralized Machine Learning](https://mlsanity.com/paper/2205.08443/) (2022)
- [Information-Theoretic Bounds on the Generalization Error and Privacy Leakage in Federated Learning](https://mlsanity.com/paper/2005.02503/) (2020)
- [Layer-wise Characterization of Latent Information Leakage in Federated Learning](https://mlsanity.com/paper/2010.08762/) (2020)
- [How to scale distributed deep learning?](https://mlsanity.com/paper/1611.04581/) (2016)
- [AGIC: Approximate Gradient Inversion Attack on Federated Learning](https://mlsanity.com/paper/2204.13784/) (2022)
- [Distributed Optimization Using the Primal-Dual Method of Multipliers](https://mlsanity.com/paper/1702.00841/) (2017)
- [A Quantitative Metric for Privacy Leakage in Federated Learning](https://mlsanity.com/paper/2102.13472/) (2021)
- [Privacy-Preserving Distributed Optimization via Subspace Perturbation: A General Framework](https://mlsanity.com/paper/2004.13999/) (2020)

## Built on by (most cited first, 6 of 6)

- [From Centralized to Decentralized Federated Learning: Theoretical Insights, Privacy Preservation, and Robustness Challenges](https://mlsanity.com/paper/2503.07505/) (2025)
- [Dynamic Topology Optimization for Non-IID Data in Decentralized Learning](https://mlsanity.com/paper/2602.03383/) (2026)
- [LAGO: Few-shot Crosslingual Embedding Inversion Attacks via Language Similarity-Aware Graph Optimization](https://mlsanity.com/paper/2505.16008/) (2025)
- [Targeted Attacks and Defenses for Distributed Federated Learning in Vehicular Networks](https://mlsanity.com/paper/2510.15109/) (2025)
- [Quantized Stochastic Primal-Dual Methods for Distributed Optimization under Relaxed Global Geometry](https://mlsanity.com/paper/2606.11339/) (2026)
- [When Topology Betrays Privacy: Lattice-Based Reconstruction Attacks on Secure Aggregation in Decentralized Federated Learning](https://mlsanity.com/paper/2609.08476/) (2026)

## Abstract (arXiv)

Federated learning (FL) emerged as a paradigm designed to improve data privacy by enabling data to reside at its source, thus embedding privacy as a core consideration in FL architectures, whether centralized or decentralized. Contrasting with recent findings by Pasquini et al., which suggest that decentralized FL does not empirically offer any additional privacy or security benefits over centralized models, our study provides compelling evidence to the contrary. We demonstrate that decentralized FL, when deploying distributed optimization, provides enhanced privacy protection - both theoretically and empirically - compared to centralized approaches. The challenge of quantifying privacy loss through iterative processes has traditionally constrained the theoretical exploration of FL protocols. We overcome this by conducting a pioneering in-depth information-theoretical privacy analysis for both frameworks. Our analysis, considering both eavesdropping and passive adversary models, successfully establishes bounds on privacy leakage. We show information theoretically that the privacy loss in decentralized FL is upper bounded by the loss in centralized FL. Compared to the centralized case where local gradients of individual participants are directly revealed, a key distinction of optimization-based decentralized FL is that the relevant information includes differences of local gradients over successive iterations and the aggregated sum of different nodes' gradients over the network. This information complicates the adversary's attempt to infer private data. To bridge our theoretical insights with practical applications, we present detailed case studies involving logistic regression and deep neural networks. These examples demonstrate that while privacy leakage remains comparable in simpler models, complex models like deep neural networks exhibit lower privacy risks under decentralized FL.