# Privacy Amplification by Decentralization

arXiv: https://arxiv.org/abs/2012.05326 · HTML: https://mlsanity.com/paper/2012.05326/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Dec 2020.

## Built on by (most cited first, 28 of 28)

- [Federated Multi-Task Learning under a Mixture of Distributions](https://mlsanity.com/paper/2108.10252/) (2021)
- [Muffliato: Peer-to-Peer Privacy Amplification for Decentralized Optimization and Averaging](https://mlsanity.com/paper/2206.05091/) (2022)
- [On the (In)security of Peer-to-Peer Decentralized Machine Learning](https://mlsanity.com/paper/2205.08443/) (2022)
- [Differentially Private Natural Language Models: Recent Advances and Future Directions](https://mlsanity.com/paper/2301.09112/) (2023)
- [Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model](https://mlsanity.com/paper/2405.14457/) (2024)
- [Network Shuffling: Privacy Amplification via Random Walks](https://mlsanity.com/paper/2204.03919/) (2022)
- [From Noisy Fixed-Point Iterations to Private ADMM for Centralized and Federated Learning](https://mlsanity.com/paper/2302.12559/) (2023)
- [Asymmetrically Decentralized Federated Learning](https://mlsanity.com/paper/2310.05093/) (2023)
- [From Centralized to Decentralized Federated Learning: Theoretical Insights, Privacy Preservation, and Robustness Challenges](https://mlsanity.com/paper/2503.07505/) (2025)
- [Straggler-Resilient Differentially-Private Decentralized Learning](https://mlsanity.com/paper/2212.03080/) (2022)
- [Mitigating Privacy-Utility Trade-off in Decentralized Federated Learning via f-Differential Privacy](https://mlsanity.com/paper/2510.19934/) (2025)
- [Boosting the Performance of Decentralized Federated Learning via Catalyst Acceleration](https://mlsanity.com/paper/2410.07272/) (2024)
- [Differential Privacy Analysis of Decentralized Gossip Averaging under Varying Threat Models](https://mlsanity.com/paper/2505.19969/) (2025)
- [Privacy Amplification Through Synthetic Data: Insights from Linear Regression](https://mlsanity.com/paper/2506.05101/) (2025)
- [Unveiling the Power of Multiple Gossip Steps: A Stability-Based Generalization Analysis in Decentralized Training](https://mlsanity.com/paper/2510.07980/) (2025)
- [Unified Privacy Guarantees for Decentralized Learning via Matrix Factorization](https://mlsanity.com/paper/2510.17480/) (2025)
- [A New Dimensionality Reduction Method Based on Hensel's Compression for Privacy Protection in Federated Learning](https://mlsanity.com/paper/2205.02089/) (2022)
- [Decentralized Hyper-Gradient Computation over Time-Varying Directed Networks](https://mlsanity.com/paper/2210.02129/) (2022)
- [Locally Differentially Private Distributed Online Learning with Guaranteed Optimality](https://mlsanity.com/paper/2306.14094/) (2023)
- [Decentralized Personalized Federated Learning](https://mlsanity.com/paper/2406.06520/) (2024)
- [OledFL: Unleashing the Potential of Decentralized Federated Learning via Opposite Lookahead Enhancement](https://mlsanity.com/paper/2410.06482/) (2024)
- [How to Securely Shuffle? A survey about Secure Shufflers for privacy-preserving computations](https://mlsanity.com/paper/2507.01487/) (2025)
- [Communication-Efficient and Privacy-Preserving Decentralized Meta-Learning](https://mlsanity.com/paper/2406.13183/) (2024)
- [Differential Privacy on Trust Graphs](https://mlsanity.com/paper/2410.12045/) (2024)
- [Privacy-Preserving Federated Learning with Differentially Private Hyperdimensional Computing](https://mlsanity.com/paper/2411.01140/) (2024)
- [Topology-Aware Differential Privacy in Hierarchical Federated Learning](https://mlsanity.com/paper/2506.19260/) (2025)
- [Stability and Generalization of Push-Sum Based Decentralized Optimization over Directed Graphs](https://mlsanity.com/paper/2602.20567/) (2026)
- [Private Decentralized Optimization with Noise Reduction and Bias Correction](https://mlsanity.com/paper/2609.27658/) (2026)

## Abstract (arXiv)

Analyzing data owned by several parties while achieving a good trade-off between utility and privacy is a key challenge in federated learning and analytics. In this work, we introduce a novel relaxation of local differential privacy (LDP) that naturally arises in fully decentralized algorithms, i.e., when participants exchange information by communicating along the edges of a network graph without central coordinator. This relaxation, that we call network DP, captures the fact that users have only a local view of the system. To show the relevance of network DP, we study a decentralized model of computation where a token performs a walk on the network graph and is updated sequentially by the party who receives it. For tasks such as real summation, histogram computation and optimization with gradient descent, we propose simple algorithms on ring and complete topologies. We prove that the privacy-utility trade-offs of our algorithms under network DP significantly improve upon what is achievable under LDP, and often match the utility of the trusted curator model. Our results show for the first time that formal privacy gains can be obtained from full decentralization. We also provide experiments to illustrate the improved utility of our approach for decentralized training with stochastic gradient descent.