Privacy-Preserving Distributed Support Vector Machines

Simone Bottoni, Stefano Braghin, Theodora S. Brisimi, Alberto Trombetta

Abstract: Federated machine learning is a promising paradigm allowing organizations to collaborate toward the training of a joint model without the need to explicitly share sensitive or business-critical datasets. Previous works demonstrated that such paradigm is not sufficient to preserve confidentiality of the training data, even to honest participants. In this work, we extend a well-known framework for training sparse Support Vector Machines in a distributed setting, while preserving data confidentiality by means of a novel non-interactive secure multiparty computation engine, that preserves data confidentiality. We formally demonstrate the security properties of the engine and provide, by means of extensive empirical evaluation, the performance of the extended framework both in terms of accuracy and execution time.