# Source Anonymity for Private Random Walk Decentralized Learning

arXiv: https://arxiv.org/abs/2505.07011 · HTML: https://mlsanity.com/paper/2505.07011/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 33 references that are in the map.
- First posted on arXiv 11 May 2025.

## Builds on (most cited first, 8 of 8)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [See through Gradients: Image Batch Recovery via GradInversion](https://mlsanity.com/paper/2104.07586/) (2021)
- [Membership Inference Attacks on Machine Learning: A Survey](https://mlsanity.com/paper/2103.07853/) (2021)
- [The Composition Theorem for Differential Privacy](https://mlsanity.com/paper/1311.0776/) (2013)
- [Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication](https://mlsanity.com/paper/1902.00340/) (2019)
- [Privacy-Preserving Machine Learning with Fully Homomorphic Encryption for Deep Neural Network](https://mlsanity.com/paper/2106.07229/) (2021)
- [Walk for Learning: A Random Walk Approach for Federated Learning from Heterogeneous Data](https://mlsanity.com/paper/2206.00737/) (2022)
- [Private Weighted Random Walk Stochastic Gradient Descent](https://mlsanity.com/paper/2009.01790/) (2020)

## Built on by (most cited first, 1 of 1)

- [RW-LoRA: Communication-Efficient Decentralized LoRA Fine-Tuning via Random Walks](https://mlsanity.com/paper/2609.00078/) (2026)

## Abstract (arXiv)

This paper considers random walk-based decentralized learning, where at each iteration of the learning process, one user updates the model and sends it to a randomly chosen neighbor until a convergence criterion is met. Preserving data privacy is a central concern and open problem in decentralized learning. We propose a privacy-preserving algorithm based on public-key cryptography and anonymization. In this algorithm, the user updates the model and encrypts the result using a distant user's public key. The encrypted result is then transmitted through the network with the goal of reaching that specific user. The key idea is to hide the source's identity so that, when the destination user decrypts the result, it does not know who the source was. The challenge is to design a network-dependent probability distribution (at the source) over the potential destinations such that, from the receiver's perspective, all users have a similar likelihood of being the source. We introduce the problem and construct a scheme that provides anonymity with theoretical guarantees. We focus on random regular graphs to establish rigorous guarantees.