Chaoning Zhang
ABSTRACT
Data hiding is one widely used approach for proving ownership through blind watermarking. Deep learning has been widely used in data hiding, for which inserting an attack simulation layer (ASL) after the watermarked image has been widely recognized as the most effective approach for improving the pipeline robustness against distortions. Despite its wide usage, the gain of enhanced robustness from ASL is usually interpreted through the lens of augmentation, while our work explores this gain from a new perspective by disentangling the forward and backward propagation of such ASL. We find that the main influential component is forward propagation instead of backward propagation. This observation motivates us to use forward ASL to make the pipeline compatible with non-differentiable and/or black-box distortion, such as lossy (JPEG) compression and photoshop effects. Extensive experiments demonstrate the efficacy of our simple approach.
- Mahdi Ahmadi, Alireza Norouzi, Nader Karimi, Shadrokh Samavi, and Ali Emami. 2020. ReDMark: Framework for residual diffusion watermarking based on deep networks. Expert Systems with Applications (2020).Google Scholar
- Farhan A Alenizi. 2017. Robust Data Hiding in Multimedia for Authentication and Ownership Protection. Ph.D. Dissertation.Google Scholar
- Shumeet Baluja. 2017. Hiding images in plain sight: Deep steganography. In NeurIPS. Google ScholarDigital Library
- Z Bao, X Luo, Y Zhang, C Yang, and F Liu. 2018. A robust image steganography on resisting JPEG compression with no side information. IETE Technical Review (2018).Google Scholar
- Preeti Bhinder, Kulbir Singh, and Neeru Jindal. 2018. Image-adaptive watermarking using maximum likelihood decoder for medical images. Multimedia Tools and Applications (2018). Google ScholarDigital Library
- Beijing Chen, Chunfei Zhou, Byeungwoo Jeon, Yuhui Zheng, and Jinwei Wang. 2018. Quaternion discrete fractional random transform for color image adaptive watermarking. Multimedia Tools and Applications (2018). Google ScholarDigital Library
- Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. 2009. ImageNet: A large-scale hierarchical image database. In CVPR.Google Scholar
- Hongchang Gao, Jian Pei, and Heng Huang. 2019. Demystifying dropout. In ICML.Google Scholar
- Giaime Ginesu, Maurizio Pintus, and Daniele D Giusto. 2012. Objective assessment of the WebP image coding algorithm. Signal Processing: Image Communication (2012). Google ScholarDigital Library
- NJ Harish, BBS Kumar, and Ashok Kusagur. 2013. Hybrid robust watermarking techniques based on DWT, DCT, and SVD. International Journal of Advanced Electrical and electronics engineering (2013).Google Scholar
- Jamie Hayes and George Danezis. 2017. Generating steganographic images via adversarial training. In NeurIPS. Google ScholarDigital Library
- Quan Huynh-Thu and Mohammed Ghanbari. 2008. Scope of validity of PSNR in image/video quality assessment. Electronics letters (2008).Google Scholar
- Bibi Isac and V Santhi. 2011. A study on digital image and video watermarking schemes using neural networks. International Journal of Computer Applications (2011).Google ScholarCross Ref
- Cong Jin and Shihui Wang. 2007. Applications of a neural network to estimate watermark embedding strength. In International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS). Google ScholarDigital Library
- Haribabu Kandi, Deepak Mishra, and Subrahmanyam RK Sai Gorthi. 2017. Exploring the learning capabilities of convolutional neural networks for robust image watermarking. Computers & Security (2017). Google ScholarDigital Library
- Xiangui Kang, Jiwu Huang, and Wenjun Zeng. 2010. Efficient general print-scanning resilient data hiding based on uniform log-polar mapping. TIFS (2010). Google ScholarDigital Library
- Diederik P Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In ICLR.Google Scholar
- Didier Le Gall. 1991. MPEG: A video compression standard for multimedia applications. Commun. ACM (1991). Google ScholarDigital Library
- Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C Lawrence Zitnick. 2014. Microsoft COCO: Common objects in context. In ECCV.Google Scholar
- Yang Liu, Mengxi Guo, Jian Zhang, Yuesheng Zhu, and Xiaodong Xie. 2019. A novel two-stage separable deep learning framework for practical blind watermarking. In ACM MM. Google ScholarDigital Library
- Wei Lu, Wei Sun, and Hongtao Lu. 2009. Robust watermarking based on DWT and nonnegative matrix factorization. Computers & Electrical Engineering (2009). Google ScholarDigital Library
- Aayush Mishra, Suraj Kumar, Aditya Nigam, and Saiful Islam. 2019. VStegNET: Video Steganography Network using Spatio-Temporal features and Micro-Bottleneck. BMVC (2019).Google Scholar
- Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Omar Fawzi, and Pascal Frossard. 2017. Universal adversarial perturbations. In CVPR.Google Scholar
- Seung-Min Mun, Seung-Hun Nam, Han-Ul Jang, Dongkyu Kim, and Heung-Kyu Lee. 2017. A robust blind watermarking using convolutional neural network. arXiv preprint arXiv:1704.03248 (2017).Google Scholar
- William B Pennebaker and Joan L Mitchell. 1992. JPEG: Still image data compression standard. Google ScholarDigital Library
- Khalid Sayood. 2017. Introduction to data compression. Google ScholarDigital Library
- Richard Shin and Dawn Song. 2017. Jpeg-resistant adversarial images. In NIPS 2017 Workshop on Machine Learning and Computer Security.Google Scholar
- Satendra Pal Singh and Gaurav Bhatnagar. 2018. A new robust watermarking system in integer DCT domain. Journal of Visual Communication and Image Representation (2018).Google Scholar
- Surya Pratap Singh, Paresh Rawat, and Sudhir Agrawal. 2012. A robust watermarking approach using DCT-DWT. International journal of emerging technology and advanced engineering (2012).Google Scholar
- Athanassios Skodras, Charilaos Christopoulos, and Touradj Ebrahimi. 2001. The jpeg 2000 still image compression standard. IEEE Signal processing magazine (2001). Google ScholarDigital Library
- Xinyu Weng, Yongzhi Li, Lu Chi, and Yadong Mu. 2018. Convolutional video steganography with temporal residual modeling. arXiv preprint arXiv:1806.02941 (2018). Google ScholarDigital Library
- Pin Wu, Yang Yang, and Xiaoqiang Li. 2018. Image-into-Image Steganography Using Deep Convolutional Network. In Pacific Rim Conference on Multimedia.Google Scholar
- Chaoning Zhang, Philipp Benz, Tooba Imtiaz, and In-So Kweon. 2020 a. Understanding Adversarial Examples from the Mutual Influence of Images and Perturbations. In CVPR.Google Scholar
- Chaoning Zhang, Philipp Benz, Adil Karjauv, and In So Kweon. 2021 a. Universal Adversarial Perturbations Through the Lens of Deep Steganography: Towards A Fourier Perspective. AAAI (2021).Google Scholar
- Chaoning Zhang, Philipp Benz, Adil Karjauv, Geng Sun, and In Kweon. 2020 b. UDH: Universal Deep Hiding for Steganography, Watermarking, and Light Field Messaging. NeurIPS (2020).Google Scholar
- Chaoning Zhang, Chenguo Lin, Philipp Benz, Kejiang Chen, Weiming Zhang, and In So Kweon. 2021 b. A Brief Survey on Deep Learning Based Data Hiding, Steganography and Watermarking. arXiv preprint arXiv:2103.01607 (2021).Google Scholar
- Jiren Zhu, Russell Kaplan, Justin Johnson, and Li Fei-Fei. 2018. Hidden: Hiding data with deep networks. In ECCV.Google Scholar
Index Terms
- Towards Robust Deep Hiding Under Non-Differentiable Distortions for Practical Blind Watermarking
Recommendations
An IWT based blind and robust image watermarking scheme using secret key matrix
In this paper, the authors have proposed a binary watermark embedding approach for protecting the copyright ownership of the gray-scale images. The proposed watermark embedding process is realized in integer wavelet transform (IWT) domain to defend the ...
A new region aware invisible robust blind watermarking approach
The multimedia revolution has made a strong impact on our society. The explosive growth of Internet access to this digital information has generated new opportunities and challenges. The ease of editing and duplicating information in the digital domain ...
Robust watermarking in DWT domain using SVD and opposition and dimensional based modified firefly algorithm
The process of authenticating a digital image by embedding a watermark into it is called digital image watermarking, which protects the image from copyright infringement. This paper proposes an optimized watermarking scheme in the discrete wavelet ...
Comments