# Privacy-Preserving, Dropout-Resilient Aggregation in Decentralized Learning

arXiv: https://arxiv.org/abs/2404.17984 · HTML: https://mlsanity.com/paper/2404.17984/

## 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 27 Apr 2024.

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

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [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)
- [Towards Federated Learning at Scale: System Design](https://mlsanity.com/paper/1902.01046/) (2019)
- [Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent](https://mlsanity.com/paper/1705.09056/) (2017)
- [Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication](https://mlsanity.com/paper/1902.00340/) (2019)
- [When the Curious Abandon Honesty: Federated Learning Is Not Private](https://mlsanity.com/paper/2112.02918/) (2021)
- [Feature Inference Attack on Model Predictions in Vertical Federated Learning](https://mlsanity.com/paper/2010.10152/) (2020)
- [LightSecAgg: a Lightweight and Versatile Design for Secure Aggregation in Federated Learning](https://mlsanity.com/paper/2109.14236/) (2021)
- [Personalized and Private Peer-to-Peer Machine Learning](https://mlsanity.com/paper/1705.08435/) (2017)
- [On the (In)Feasibility of Attribute Inference Attacks on Machine Learning Models](https://mlsanity.com/paper/2103.07101/) (2021)
- [Efficient Differentially Private Secure Aggregation for Federated Learning via Hardness of Learning with Errors](https://mlsanity.com/paper/2112.06872/) (2021)
- [On the (In)security of Peer-to-Peer Decentralized Machine Learning](https://mlsanity.com/paper/2205.08443/) (2022)
- [Topology-aware Differential Privacy for Decentralized Image Classification](https://mlsanity.com/paper/2006.07817/) (2020)
- [On the Communication Complexity of Secure Computation](https://mlsanity.com/paper/1311.7584/) (2013)
- [Privacy-preserving Logistic Regression with Secret Sharing](https://mlsanity.com/paper/2105.06869/) (2021)
- [Privacy-preserving Decentralized Deep Learning with Multiparty Homomorphic Encryption](https://mlsanity.com/paper/2207.04604/) (2022)

## Abstract (arXiv)

Decentralized learning (DL) offers a novel paradigm in machine learning by distributing training across clients without central aggregation, enhancing scalability and efficiency. However, DL's peer-to-peer model raises challenges in protecting against inference attacks and privacy leaks. By forgoing central bottlenecks, DL demands privacy-preserving aggregation methods to protect data from 'honest but curious' clients and adversaries, maintaining network-wide privacy. Privacy-preserving DL faces the additional hurdle of client dropout, clients not submitting updates due to connectivity problems or unavailability, further complicating aggregation. This work proposes three secret sharing-based dropout resilience approaches for privacy-preserving DL. Our study evaluates the efficiency, performance, and accuracy of these protocols through experiments on datasets such as MNIST, Fashion-MNIST, SVHN, and CIFAR-10. We compare our protocols with traditional secret-sharing solutions across scenarios, including those with up to 1000 clients. Evaluations show that our protocols significantly outperform conventional methods, especially in scenarios with up to 30% of clients dropout and model sizes of up to 106 parameters. Our approaches demonstrate markedly high efficiency with larger models, higher dropout rates, and extensive client networks, highlighting their effectiveness in enhancing decentralized learning systems' privacy and dropout robustness.