The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Neste artigo, propomos aprendizado de dicionário seguro baseado em uma transformada unitária aleatória para representação esparsa. Atualmente, a computação em nuvem de ponta está se espalhando para muitos campos de aplicação, incluindo serviços que usam codificação esparsa. Esta situação levanta muitas novas preocupações com a privacidade. A computação em nuvem de borda apresenta vários problemas sérios para os usuários finais, como uso não autorizado e vazamento de dados, além de falhas de privacidade. O esquema proposto fornece algoritmos práticos de aprendizado de dicionário MOD e K-SVD que permitem a computação em sinais criptografados. Provamos, teoricamente, que a proposta tem exatamente o mesmo desempenho de estimativa de aprendizado de dicionário que a variante não criptografada dos algoritmos MOD e K-SVD. Nós o aplicamos à modelagem segura de imagens com base em um modelo de patch de imagem. Por fim, demonstramos seu desempenho em dados sintéticos e em uma aplicação segura de modelagem de imagens para imagens naturais.
Takayuki NAKACHI
NTT Corporation
Yukihiro BANDOH
NTT Corporation
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.
Copiar
Takayuki NAKACHI, Yukihiro BANDOH, Hitoshi KIYA, "Secure Overcomplete Dictionary Learning for Sparse Representation" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 1, pp. 50-58, January 2020, doi: 10.1587/transinf.2019MUP0009.
Abstract: In this paper, we propose secure dictionary learning based on a random unitary transform for sparse representation. Currently, edge cloud computing is spreading to many application fields including services that use sparse coding. This situation raises many new privacy concerns. Edge cloud computing poses several serious issues for end users, such as unauthorized use and leak of data, and privacy failures. The proposed scheme provides practical MOD and K-SVD dictionary learning algorithms that allow computation on encrypted signals. We prove, theoretically, that the proposal has exactly the same dictionary learning estimation performance as the non-encrypted variant of MOD and K-SVD algorithms. We apply it to secure image modeling based on an image patch model. Finally, we demonstrate its performance on synthetic data and a secure image modeling application for natural images.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019MUP0009/_p
Copiar
@ARTICLE{e103-d_1_50,
author={Takayuki NAKACHI, Yukihiro BANDOH, Hitoshi KIYA, },
journal={IEICE TRANSACTIONS on Information},
title={Secure Overcomplete Dictionary Learning for Sparse Representation},
year={2020},
volume={E103-D},
number={1},
pages={50-58},
abstract={In this paper, we propose secure dictionary learning based on a random unitary transform for sparse representation. Currently, edge cloud computing is spreading to many application fields including services that use sparse coding. This situation raises many new privacy concerns. Edge cloud computing poses several serious issues for end users, such as unauthorized use and leak of data, and privacy failures. The proposed scheme provides practical MOD and K-SVD dictionary learning algorithms that allow computation on encrypted signals. We prove, theoretically, that the proposal has exactly the same dictionary learning estimation performance as the non-encrypted variant of MOD and K-SVD algorithms. We apply it to secure image modeling based on an image patch model. Finally, we demonstrate its performance on synthetic data and a secure image modeling application for natural images.},
keywords={},
doi={10.1587/transinf.2019MUP0009},
ISSN={1745-1361},
month={January},}
Copiar
TY - JOUR
TI - Secure Overcomplete Dictionary Learning for Sparse Representation
T2 - IEICE TRANSACTIONS on Information
SP - 50
EP - 58
AU - Takayuki NAKACHI
AU - Yukihiro BANDOH
AU - Hitoshi KIYA
PY - 2020
DO - 10.1587/transinf.2019MUP0009
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2020
AB - In this paper, we propose secure dictionary learning based on a random unitary transform for sparse representation. Currently, edge cloud computing is spreading to many application fields including services that use sparse coding. This situation raises many new privacy concerns. Edge cloud computing poses several serious issues for end users, such as unauthorized use and leak of data, and privacy failures. The proposed scheme provides practical MOD and K-SVD dictionary learning algorithms that allow computation on encrypted signals. We prove, theoretically, that the proposal has exactly the same dictionary learning estimation performance as the non-encrypted variant of MOD and K-SVD algorithms. We apply it to secure image modeling based on an image patch model. Finally, we demonstrate its performance on synthetic data and a secure image modeling application for natural images.
ER -