We propose a privacy-preserving machine learning scheme with encryption-then-compression (EtC) images, where EtC images are images encrypted by using a block-based encryption method proposed for EtC systems with JPEG compression. In this paper, a novel property of EtC images is first discussed, although EtC ones was already shown to be compressible as a property. The novel property allows us to directly apply EtC images to machine learning algorithms non-specialized for computing encrypted data. In addition, the proposed scheme is demonstrated to provide no degradation in the performance of some typical machine learning algorithms including the support vector machine algorithm with kernel trick and random forests under the use of z-score normalization. A number of facial recognition experiments with are carried out to confirm the effectiveness of the proposed scheme.
Ayana KAWAMURA
Tokyo Metropolitan University
Yuma KINOSHITA
Tokyo Metropolitan University
Takayuki NAKACHI
NTT Corporation
Sayaka SHIOTA
Tokyo Metropolitan University
Hitoshi KIYA
Tokyo Metropolitan University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Ayana KAWAMURA, Yuma KINOSHITA, Takayuki NAKACHI, Sayaka SHIOTA, Hitoshi KIYA, "A Privacy-Preserving Machine Learning Scheme Using EtC Images" in IEICE TRANSACTIONS on Fundamentals,
vol. E103-A, no. 12, pp. 1571-1578, December 2020, doi: 10.1587/transfun.2020SMP0022.
Abstract: We propose a privacy-preserving machine learning scheme with encryption-then-compression (EtC) images, where EtC images are images encrypted by using a block-based encryption method proposed for EtC systems with JPEG compression. In this paper, a novel property of EtC images is first discussed, although EtC ones was already shown to be compressible as a property. The novel property allows us to directly apply EtC images to machine learning algorithms non-specialized for computing encrypted data. In addition, the proposed scheme is demonstrated to provide no degradation in the performance of some typical machine learning algorithms including the support vector machine algorithm with kernel trick and random forests under the use of z-score normalization. A number of facial recognition experiments with are carried out to confirm the effectiveness of the proposed scheme.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2020SMP0022/_p
Copy
@ARTICLE{e103-a_12_1571,
author={Ayana KAWAMURA, Yuma KINOSHITA, Takayuki NAKACHI, Sayaka SHIOTA, Hitoshi KIYA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={A Privacy-Preserving Machine Learning Scheme Using EtC Images},
year={2020},
volume={E103-A},
number={12},
pages={1571-1578},
abstract={We propose a privacy-preserving machine learning scheme with encryption-then-compression (EtC) images, where EtC images are images encrypted by using a block-based encryption method proposed for EtC systems with JPEG compression. In this paper, a novel property of EtC images is first discussed, although EtC ones was already shown to be compressible as a property. The novel property allows us to directly apply EtC images to machine learning algorithms non-specialized for computing encrypted data. In addition, the proposed scheme is demonstrated to provide no degradation in the performance of some typical machine learning algorithms including the support vector machine algorithm with kernel trick and random forests under the use of z-score normalization. A number of facial recognition experiments with are carried out to confirm the effectiveness of the proposed scheme.},
keywords={},
doi={10.1587/transfun.2020SMP0022},
ISSN={1745-1337},
month={December},}
Copy
TY - JOUR
TI - A Privacy-Preserving Machine Learning Scheme Using EtC Images
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1571
EP - 1578
AU - Ayana KAWAMURA
AU - Yuma KINOSHITA
AU - Takayuki NAKACHI
AU - Sayaka SHIOTA
AU - Hitoshi KIYA
PY - 2020
DO - 10.1587/transfun.2020SMP0022
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E103-A
IS - 12
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - December 2020
AB - We propose a privacy-preserving machine learning scheme with encryption-then-compression (EtC) images, where EtC images are images encrypted by using a block-based encryption method proposed for EtC systems with JPEG compression. In this paper, a novel property of EtC images is first discussed, although EtC ones was already shown to be compressible as a property. The novel property allows us to directly apply EtC images to machine learning algorithms non-specialized for computing encrypted data. In addition, the proposed scheme is demonstrated to provide no degradation in the performance of some typical machine learning algorithms including the support vector machine algorithm with kernel trick and random forests under the use of z-score normalization. A number of facial recognition experiments with are carried out to confirm the effectiveness of the proposed scheme.
ER -