Soteria: Preserving Privacy in Distributed Machine Learning

• Tipo: Artigo em Livro de Atas de Conferência Internacional
• Data: 2023

Autores

Brito, C (Autor) Outra; Ferreira, P (Autor) FCUP; Portela, B (Autor) FCUP; Oliveira, R (Autor) Outra; Paulo, J (Autor) Outra

Ata de Conferência Internacional

Título: Proceedings of the ACM Symposium on Applied Computing

Páginas: 135-142

38th Annual ACM Symposium on Applied Computing, SAC 2023

27 March 2023 through 31 March 2023

Indexação

ISI Web of Knowledge - 3 Citações

Scopus - 7 Citações

Outras Informações

ID Authenticus: P-00Y-N65

DOI: 10.1145/3555776.3578591

Abstract (EN): We propose Soteria, a system for distributed privacy-preserving Machine Learning (ML) that leverages Trusted Execution Environments (e.g. Intel SGX) to run code in isolated containers (enclaves). Unlike previous work, where all ML-related computation is performed at trusted enclaves, we introduce a hybrid scheme, combining computation done inside and outside these enclaves. The conducted experimental evaluation validates that our approach reduces the runtime of ML algorithms by up to 41%, when compared to previous related work. Our protocol is accompanied by a security proof, as well as a discussion regarding resilience against a wide spectrum of ML attacks.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 8