Perceptual Hashing based on Machine Learning for Blockchain and Digital Watermarking

Zhaoxiong Meng, Tetsuya Morizumi, Sumiko Miyata, Hirotsugu Kinoshita

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In our previous study, we found three requirements for digital watermarking. The first is that to prevent watermark information of an image from being diverted to other images, this information must be generated based on the original image. The second is that after the original image is modified/edited, it should still be able to be used the same as the original image. The third is that multiple digital watermarks should be stored and managed without relying on trusted third parties. To meet these requirements, we proposed a digital-copyright-management system based on perceptual hashing and blockchain. However, because we used conventional perceptual hashing in that study, we could not draw sufficient conclusions about the first and second requirements. In this current study, to obtain a stable message digest, we propose a method of improving perceptual hashing based on machine learning. With this method, an image is first modified/edited using various methods to generate an image set. This image set is then input into a convolutional neural network (CNN) to calculate the features of the images, and the data of the CNN intermediate layer are output as machine learning data. Finally, through machine learning, latent stochastic variables are determined that can be used to calculate latent image features, and the perceptual hash value of this image set is calculated using these image features for the blockchain and digital watermarking. The method also records these latent stochastic variables on the blockchain to ensure copyright security by ensuring that these variables cannot be used by those other than the original author.

Original languageEnglish
Title of host publicationProceedings of the 3rd World Conference on Smart Trends in Systems, Security and Sustainability, WorldS4 2019
EditorsXin-She Yang, Nilanjan Dey, Amit Joshi
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages193-198
Number of pages6
ISBN (Electronic)9781728137803
DOIs
Publication statusPublished - 2019 Jul
Event3rd World Conference on Smart Trends in Systems, Security and Sustainability, WorldS4 2019 - London, United Kingdom
Duration: 2019 Jul 302019 Jul 31

Publication series

NameProceedings of the 3rd World Conference on Smart Trends in Systems, Security and Sustainability, WorldS4 2019

Conference

Conference3rd World Conference on Smart Trends in Systems, Security and Sustainability, WorldS4 2019
CountryUnited Kingdom
CityLondon
Period19/7/3019/7/31

Fingerprint

Digital watermarking
Learning systems
learning
Neural networks
neural network
Machine learning
management

Keywords

  • Blockchain
  • Digital copyright management
  • Digital watermarking
  • Machine learning
  • perceptual hashing

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Information Systems and Management
  • Renewable Energy, Sustainability and the Environment
  • Safety, Risk, Reliability and Quality
  • Education

Cite this

Meng, Z., Morizumi, T., Miyata, S., & Kinoshita, H. (2019). Perceptual Hashing based on Machine Learning for Blockchain and Digital Watermarking. In X-S. Yang, N. Dey, & A. Joshi (Eds.), Proceedings of the 3rd World Conference on Smart Trends in Systems, Security and Sustainability, WorldS4 2019 (pp. 193-198). [8903993] (Proceedings of the 3rd World Conference on Smart Trends in Systems, Security and Sustainability, WorldS4 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WorldS4.2019.8903993

Perceptual Hashing based on Machine Learning for Blockchain and Digital Watermarking. / Meng, Zhaoxiong; Morizumi, Tetsuya; Miyata, Sumiko; Kinoshita, Hirotsugu.

Proceedings of the 3rd World Conference on Smart Trends in Systems, Security and Sustainability, WorldS4 2019. ed. / Xin-She Yang; Nilanjan Dey; Amit Joshi. Institute of Electrical and Electronics Engineers Inc., 2019. p. 193-198 8903993 (Proceedings of the 3rd World Conference on Smart Trends in Systems, Security and Sustainability, WorldS4 2019).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Meng, Z, Morizumi, T, Miyata, S & Kinoshita, H 2019, Perceptual Hashing based on Machine Learning for Blockchain and Digital Watermarking. in X-S Yang, N Dey & A Joshi (eds), Proceedings of the 3rd World Conference on Smart Trends in Systems, Security and Sustainability, WorldS4 2019., 8903993, Proceedings of the 3rd World Conference on Smart Trends in Systems, Security and Sustainability, WorldS4 2019, Institute of Electrical and Electronics Engineers Inc., pp. 193-198, 3rd World Conference on Smart Trends in Systems, Security and Sustainability, WorldS4 2019, London, United Kingdom, 19/7/30. https://doi.org/10.1109/WorldS4.2019.8903993
Meng Z, Morizumi T, Miyata S, Kinoshita H. Perceptual Hashing based on Machine Learning for Blockchain and Digital Watermarking. In Yang X-S, Dey N, Joshi A, editors, Proceedings of the 3rd World Conference on Smart Trends in Systems, Security and Sustainability, WorldS4 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 193-198. 8903993. (Proceedings of the 3rd World Conference on Smart Trends in Systems, Security and Sustainability, WorldS4 2019). https://doi.org/10.1109/WorldS4.2019.8903993
Meng, Zhaoxiong ; Morizumi, Tetsuya ; Miyata, Sumiko ; Kinoshita, Hirotsugu. / Perceptual Hashing based on Machine Learning for Blockchain and Digital Watermarking. Proceedings of the 3rd World Conference on Smart Trends in Systems, Security and Sustainability, WorldS4 2019. editor / Xin-She Yang ; Nilanjan Dey ; Amit Joshi. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 193-198 (Proceedings of the 3rd World Conference on Smart Trends in Systems, Security and Sustainability, WorldS4 2019).
@inproceedings{beb74dbe1ff34a838df6570f7c61fca0,
title = "Perceptual Hashing based on Machine Learning for Blockchain and Digital Watermarking",
abstract = "In our previous study, we found three requirements for digital watermarking. The first is that to prevent watermark information of an image from being diverted to other images, this information must be generated based on the original image. The second is that after the original image is modified/edited, it should still be able to be used the same as the original image. The third is that multiple digital watermarks should be stored and managed without relying on trusted third parties. To meet these requirements, we proposed a digital-copyright-management system based on perceptual hashing and blockchain. However, because we used conventional perceptual hashing in that study, we could not draw sufficient conclusions about the first and second requirements. In this current study, to obtain a stable message digest, we propose a method of improving perceptual hashing based on machine learning. With this method, an image is first modified/edited using various methods to generate an image set. This image set is then input into a convolutional neural network (CNN) to calculate the features of the images, and the data of the CNN intermediate layer are output as machine learning data. Finally, through machine learning, latent stochastic variables are determined that can be used to calculate latent image features, and the perceptual hash value of this image set is calculated using these image features for the blockchain and digital watermarking. The method also records these latent stochastic variables on the blockchain to ensure copyright security by ensuring that these variables cannot be used by those other than the original author.",
keywords = "Blockchain, Digital copyright management, Digital watermarking, Machine learning, perceptual hashing",
author = "Zhaoxiong Meng and Tetsuya Morizumi and Sumiko Miyata and Hirotsugu Kinoshita",
year = "2019",
month = "7",
doi = "10.1109/WorldS4.2019.8903993",
language = "English",
series = "Proceedings of the 3rd World Conference on Smart Trends in Systems, Security and Sustainability, WorldS4 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "193--198",
editor = "Xin-She Yang and Nilanjan Dey and Amit Joshi",
booktitle = "Proceedings of the 3rd World Conference on Smart Trends in Systems, Security and Sustainability, WorldS4 2019",

}

TY - GEN

T1 - Perceptual Hashing based on Machine Learning for Blockchain and Digital Watermarking

AU - Meng, Zhaoxiong

AU - Morizumi, Tetsuya

AU - Miyata, Sumiko

AU - Kinoshita, Hirotsugu

PY - 2019/7

Y1 - 2019/7

N2 - In our previous study, we found three requirements for digital watermarking. The first is that to prevent watermark information of an image from being diverted to other images, this information must be generated based on the original image. The second is that after the original image is modified/edited, it should still be able to be used the same as the original image. The third is that multiple digital watermarks should be stored and managed without relying on trusted third parties. To meet these requirements, we proposed a digital-copyright-management system based on perceptual hashing and blockchain. However, because we used conventional perceptual hashing in that study, we could not draw sufficient conclusions about the first and second requirements. In this current study, to obtain a stable message digest, we propose a method of improving perceptual hashing based on machine learning. With this method, an image is first modified/edited using various methods to generate an image set. This image set is then input into a convolutional neural network (CNN) to calculate the features of the images, and the data of the CNN intermediate layer are output as machine learning data. Finally, through machine learning, latent stochastic variables are determined that can be used to calculate latent image features, and the perceptual hash value of this image set is calculated using these image features for the blockchain and digital watermarking. The method also records these latent stochastic variables on the blockchain to ensure copyright security by ensuring that these variables cannot be used by those other than the original author.

AB - In our previous study, we found three requirements for digital watermarking. The first is that to prevent watermark information of an image from being diverted to other images, this information must be generated based on the original image. The second is that after the original image is modified/edited, it should still be able to be used the same as the original image. The third is that multiple digital watermarks should be stored and managed without relying on trusted third parties. To meet these requirements, we proposed a digital-copyright-management system based on perceptual hashing and blockchain. However, because we used conventional perceptual hashing in that study, we could not draw sufficient conclusions about the first and second requirements. In this current study, to obtain a stable message digest, we propose a method of improving perceptual hashing based on machine learning. With this method, an image is first modified/edited using various methods to generate an image set. This image set is then input into a convolutional neural network (CNN) to calculate the features of the images, and the data of the CNN intermediate layer are output as machine learning data. Finally, through machine learning, latent stochastic variables are determined that can be used to calculate latent image features, and the perceptual hash value of this image set is calculated using these image features for the blockchain and digital watermarking. The method also records these latent stochastic variables on the blockchain to ensure copyright security by ensuring that these variables cannot be used by those other than the original author.

KW - Blockchain

KW - Digital copyright management

KW - Digital watermarking

KW - Machine learning

KW - perceptual hashing

UR - http://www.scopus.com/inward/record.url?scp=85075863283&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85075863283&partnerID=8YFLogxK

U2 - 10.1109/WorldS4.2019.8903993

DO - 10.1109/WorldS4.2019.8903993

M3 - Conference contribution

AN - SCOPUS:85075863283

T3 - Proceedings of the 3rd World Conference on Smart Trends in Systems, Security and Sustainability, WorldS4 2019

SP - 193

EP - 198

BT - Proceedings of the 3rd World Conference on Smart Trends in Systems, Security and Sustainability, WorldS4 2019

A2 - Yang, Xin-She

A2 - Dey, Nilanjan

A2 - Joshi, Amit

PB - Institute of Electrical and Electronics Engineers Inc.

ER -