Secure Machine Learning in the Cloud Using One Way Scrambling by Deconvolution

Yiftach Savransky, Roni Mateless, Gilad Katz

Research output: Working paper/PreprintPreprint

52 Downloads (Pure)

Abstract

Cloud-based machine learning services (CMLS) enable organizations to take advantage of advanced models that are pre-trained on large quantities of data. The main shortcoming of using these services, however, is the difficulty of keeping the transmitted data private and secure. Asymmetric encryption requires the data to be decrypted in the cloud, while Homomorphic encryption is often too slow and difficult to implement. We propose One Way Scrambling by Deconvolution (OWSD), a deconvolution-based scrambling framework that offers the advantages of Homomorphic encryption at a fraction of the computational overhead. Extensive evaluation on multiple image datasets demonstrates OWSD's ability to achieve near-perfect classification performance when the output vector of the CMLS is sufficiently large. Additionally, we provide empirical analysis of the robustness of our approach.
Original languageEnglish
DOIs
StatePublished - 1 Nov 2021

Keywords

  • Computer Science - Cryptography and Security
  • Computer Science - Machine Learning

Fingerprint

Dive into the research topics of 'Secure Machine Learning in the Cloud Using One Way Scrambling by Deconvolution'. Together they form a unique fingerprint.

Cite this