TY - UNPB
T1 - Secure Machine Learning in the Cloud Using One Way Scrambling by Deconvolution
AU - Savransky, Yiftach
AU - Mateless, Roni
AU - Katz, Gilad
PY - 2021/11/1
Y1 - 2021/11/1
N2 - 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.
AB - 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.
KW - Computer Science - Cryptography and Security
KW - Computer Science - Machine Learning
M3 - פרסום מוקדם
BT - Secure Machine Learning in the Cloud Using One Way Scrambling by Deconvolution
ER -