Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/90762
Título: | SOTERIA: Preserving privacy in distributed machine learning |
Autor(es): | Brito, Cláudia Vanessa Martins Ferreira, Pedro G. Portela, Bernardo Oliveira, Rui Carlos Mendes de Paulo, João |
Palavras-chave: | apache spark Intel SGX machine learning privacy-preserving |
Data: | 2023 |
Editora: | ACM |
Citação: | Brito, C., Ferreira, P., Portela, B., Oliveira, R., & Paulo, J. (2023, March 27). SOTERIA: Preserving Privacy in Distributed Machine Learning. Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing. ACM. http://doi.org/10.1145/3555776.3578591 |
Resumo(s): | 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. |
Tipo: | Artigo em ata de conferência |
URI: | https://hdl.handle.net/1822/90762 |
ISBN: | 9781450395175 |
DOI: | 10.1145/3555776.3578591 |
Versão da editora: | https://dl.acm.org/doi/10.1145/3555776.3578591 |
Arbitragem científica: | yes |
Acesso: | Acesso restrito UMinho |
Aparece nas coleções: | HASLab - Artigos em revistas internacionais |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
3555776 3578591.pdf Acesso restrito! | 1,63 MB | Adobe PDF | Ver/Abrir |