Soteria: Preserving Privacy in Distributed Machine Learning

• Type: Article in International Conference Proceedings Book
• Date: 2023

Authors

Brito, C (Author) Other; Ferreira, P (Author) FCUP; Portela, B (Author) FCUP; Oliveira, R (Author) Other; Paulo, J (Author) Other

Conference proceedings International

Title: Proceedings of the ACM Symposium on Applied Computing

Pages: 135-142

38th Annual ACM Symposium on Applied Computing, SAC 2023

27 March 2023 through 31 March 2023

Indexing

ISI Web of Knowledge - 1 Citation

Scopus - 3 Citations

Other information

Authenticus ID: 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.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 8