paper-with-me

Papers

Secure Aggregation Meets Sparsification in Decentralized Learning

2024-05-13 · Sayan Biswas, Anne-Marie Kermarrec, Rafael Pires, Rishi Sharma, Milos Vujasinovic

Decentralized learning (DL) faces increased vulnerability to privacy breaches due to sophisticated attacks on machine learning (ML) models. Secure aggregation is a computationally efficient cryptographic technique that enables multiple parties to compute an aggregate of their private data while keeping their individual inputs concealed from each other and from any central aggregator. To enhance communication efficiency in DL, sparsification techniques are used, selectively sharing only the most crucial parameters or gradients in a model, thereby maintaining efficiency without notably compromising accuracy. However, applying secure aggregation to sparsified models in DL is challenging due to the transmission of disjoint parameter sets by distinct nodes, which can prevent masks from canceling out effectively. This paper introduces CESAR, a novel secure aggregation protocol for DL designed to be compatible with existing sparsification mechanisms. CESAR provably defends against honest-but-curious adversaries and can be formally adapted to counteract collusion between them. We provide a foundational understanding of the interaction between the sparsification carried out by the nodes and the proportion of the parameters shared under CESAR in both colluding and non-colluding environments, offering analytical insight into the working and applicability of the protocol. Experiments on a network with 48 nodes in a 3-regular topology show that with random subsampling, CESAR is always within 0.5% accuracy of decentralized parallel stochastic gradient descent (D-PSGD), while adding only 11% of data overhead. Moreover, it surpasses the accuracy on TopK by up to 0.3% on independent and identically distributed (IID) data.

📄 PDF Abstract BibTeX arXiv:2405.07708

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Secure Aggregation with Top-K Sparsification in Decentralized Federated Learning

2026-06-09 · Hengxuan Tang, Jinbao Zhu, Xiaohu Tang arxiv

Secure aggregation is a vital component for mitigating gradient leakage in federated learning, but its communication cost conventionally scales with the gradient dimension. This becomes prohibitive for large models and e…

Federated Learning

Sparsified Secure Aggregation for Privacy-Preserving Federated Learning

2021-12-23 · Irem Ergun, Hasin Us Sami, Basak Guler

Secure aggregation is a popular protocol in privacy-preserving federated learning, which allows model aggregation without revealing the individual models in the clear. On the other hand, conventional secure aggregation p…

Federated LearningPrivacy Preserving

Decentralized Learning Made Easy with DecentralizePy

2023-04-17 · Akash Dhasade, Anne-Marie Kermarrec, Rafael Pires, Rishi Sharma 외

Decentralized learning (DL) has gained prominence for its potential benefits in terms of scalability, privacy, and fault tolerance. It consists of many nodes that coordinate without a central server and exchange millions…

Efficient and Secure Federated Learning for Financial Applications

2023-03-15 · Tao Liu, Zhi Wang, Hui He, Liangliang Lin 외

The conventional machine learning (ML) and deep learning approaches need to share customers' sensitive information with an external credit bureau to generate a prediction model that opens the door to privacy leakage. Thi…

Federated Learning

Information-Theoretic Decentralized Secure Aggregation with Passive Collusion Resilience

2025-08-01 · Xiang Zhang, Zhou Li, Shuangyang Li, Kai Wan 외 arxiv

In decentralized federated learning (FL), multiple clients collaboratively learn a shared machine learning (ML) model by leveraging their privately held datasets distributed across the network, through interactive exchan…

Federated Learning