IEICE TRANSACTIONS on Information
Neural Watermarking Method Including an Attack Simulator against Rotation and Compression Attacks
Summary :
We have developed a digital watermarking method that use neural networks to learn embedding and extraction processes that are robust against rotation and JPEG compression. The proposed neural networks consist of a stego-image generator, a watermark extractor, a stego-image discriminator, and an attack simulator. The attack simulator consists of a rotation layer and an additive noise layer, which simulate the rotation attack and the JPEG compression attack, respectively. The stego-image generator can learn embedding that is robust against these attacks, and also, the watermark extractor can extract watermarks without rotation synchronization. The quality of the stego-images can be improved by using the stego-image discriminator, which is a type of adversarial network. We evaluated the robustness of the watermarks and image quality and found that, using the proposed method, high-quality stego-images could be generated and the neural networks could be trained to embed and extract watermarks that are robust against rotation and JPEG compression attacks. We also showed that the robustness and image quality can be adjusted by changing the noise strength in the noise layer.
- Publication
- IEICE TRANSACTIONS on Information Vol.E103-D No.1 pp.33-41
- Publication Date
- 2020/01/01
- Publicized
- 2019/10/23
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2019MUP0007
- Type of Manuscript
- Special Section PAPER (Special Section on Enriched Multimedia — Application of Multimedia Technology and Its Security —)
- Category
Authors
Ippei HAMAMOTO
Yamaguchi University
Masaki KAWAMURA
Yamaguchi University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
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.
Cite this
Copy
Ippei HAMAMOTO, Masaki KAWAMURA, "Neural Watermarking Method Including an Attack Simulator against Rotation and Compression Attacks" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 1, pp. 33-41, January 2020, doi: 10.1587/transinf.2019MUP0007.
Abstract: We have developed a digital watermarking method that use neural networks to learn embedding and extraction processes that are robust against rotation and JPEG compression. The proposed neural networks consist of a stego-image generator, a watermark extractor, a stego-image discriminator, and an attack simulator. The attack simulator consists of a rotation layer and an additive noise layer, which simulate the rotation attack and the JPEG compression attack, respectively. The stego-image generator can learn embedding that is robust against these attacks, and also, the watermark extractor can extract watermarks without rotation synchronization. The quality of the stego-images can be improved by using the stego-image discriminator, which is a type of adversarial network. We evaluated the robustness of the watermarks and image quality and found that, using the proposed method, high-quality stego-images could be generated and the neural networks could be trained to embed and extract watermarks that are robust against rotation and JPEG compression attacks. We also showed that the robustness and image quality can be adjusted by changing the noise strength in the noise layer.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019MUP0007/_p
Copy
@ARTICLE{e103-d_1_33,
author={Ippei HAMAMOTO, Masaki KAWAMURA, },
journal={IEICE TRANSACTIONS on Information},
title={Neural Watermarking Method Including an Attack Simulator against Rotation and Compression Attacks},
year={2020},
volume={E103-D},
number={1},
pages={33-41},
abstract={We have developed a digital watermarking method that use neural networks to learn embedding and extraction processes that are robust against rotation and JPEG compression. The proposed neural networks consist of a stego-image generator, a watermark extractor, a stego-image discriminator, and an attack simulator. The attack simulator consists of a rotation layer and an additive noise layer, which simulate the rotation attack and the JPEG compression attack, respectively. The stego-image generator can learn embedding that is robust against these attacks, and also, the watermark extractor can extract watermarks without rotation synchronization. The quality of the stego-images can be improved by using the stego-image discriminator, which is a type of adversarial network. We evaluated the robustness of the watermarks and image quality and found that, using the proposed method, high-quality stego-images could be generated and the neural networks could be trained to embed and extract watermarks that are robust against rotation and JPEG compression attacks. We also showed that the robustness and image quality can be adjusted by changing the noise strength in the noise layer.},
keywords={},
doi={10.1587/transinf.2019MUP0007},
ISSN={1745-1361},
month={January},}
Copy
TY - JOUR
TI - Neural Watermarking Method Including an Attack Simulator against Rotation and Compression Attacks
T2 - IEICE TRANSACTIONS on Information
SP - 33
EP - 41
AU - Ippei HAMAMOTO
AU - Masaki KAWAMURA
PY - 2020
DO - 10.1587/transinf.2019MUP0007
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2020
AB - We have developed a digital watermarking method that use neural networks to learn embedding and extraction processes that are robust against rotation and JPEG compression. The proposed neural networks consist of a stego-image generator, a watermark extractor, a stego-image discriminator, and an attack simulator. The attack simulator consists of a rotation layer and an additive noise layer, which simulate the rotation attack and the JPEG compression attack, respectively. The stego-image generator can learn embedding that is robust against these attacks, and also, the watermark extractor can extract watermarks without rotation synchronization. The quality of the stego-images can be improved by using the stego-image discriminator, which is a type of adversarial network. We evaluated the robustness of the watermarks and image quality and found that, using the proposed method, high-quality stego-images could be generated and the neural networks could be trained to embed and extract watermarks that are robust against rotation and JPEG compression attacks. We also showed that the robustness and image quality can be adjusted by changing the noise strength in the noise layer.
ER -
English
