Secure Aggregation Meets Sparsification in Decentralized Learning

arXiv:2405.07708v1 Announce Type: new
Abstract: 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 …

abstract aggregation arxiv attacks breaches compute cs.lg data decentralized inputs machine machine learning multiple parties privacy private data type vulnerability while