High-Frequency Artifacts-Resistant Image Watermarking Applicable to Image Processing Models
Source abstract
Abstract
With the extensive adoption of generative models across various domains, the protection of copyright for these models has become increasingly vital. Some researchers suggest embedding watermarks in the images generated by these models as a means of preserving IP rights. In this paper, we find that existing generative model watermarking introduces high-frequency artifacts in the high-frequency spectrum of the marked images, thereby compromising the imperceptibility and security of the generative model watermarking system. Given this revelation, we propose an innovative image watermarking technology that takes into account frequency-domain imperceptibility. Our approach abandons the conventional convolutional neural network (CNN) structure typically used as the watermarking embedding network in popular watermarking techniques. This helps the image watermarking system to avoid the inherent high-frequency artifacts commonly produced by CNNs. In addition, we design a frequency perturbation generation network to generate low-frequency perturbations. These perturbations are subsequently added as watermarks to the low-frequency components of the carrier image, thus minimizing the impact of the watermark embedding process on the high-frequency properties of the image. The results show that our proposed watermarking framework can effectively embed low-frequency perturbation watermarks into images and effectively suppress high-frequency artifacts in images, thus significantly improving the frequency-domain imperceptibility and security of the image watermarking system. The introduced approach enhances the average invisibility performance in the frequency domain by up to 24.9% when contrasted with prior methods. Moreover, the method attains superior image quality (>50 dB) in the spatial domain, accompanied by a 100% success rate in watermark extraction in the absence of attacks. This underscores its capability to uphold the efficacy of the protected network and preserve the integrity of the watermarking process. It always maintains excellent imperceptibility and robustness. Thus, the framework shows great potential as a state-of-the-art solution for protecting intellectual property.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Steganography and Watermarking Techniques · Digital Media Forensic Detection · Generative Adversarial Networks and Image Synthesis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Communication and Information Engineering, Shanghai University, Shanghai 200444, China
Funding
National Natural Science Foundation of China (NSFC)
References (36)
Show source-provided references
1. A Style-Based Generator Architecture for Generative Adversarial Networks10.1109/TPAMI.2020.2970919 ↗
2. Training language models to follow instructions with human feedback
3. Rombach, R., Blattmann, A., Lorenz, D., Esser, P., and Ommer, B. (2022, January 18–24). High-Resolution Image Synthesis with Latent Diffusion Models. Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.01042 ↗
4. Uchida, Y., Nagai, Y., Sakazawa, S., and Satoh, S. (2017, January 6–9). Embedding Watermarks into Deep Neural Networks. Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval, ICMR’17, New York, NY, USA.10.1145/3078971.3078974 ↗
5. Darvish Rouhani, B., Chen, H., and Koushanfar, F. (2019, January 13–17). DeepSigns: An End-to-End Watermarking Framework for Ownership Protection of Deep Neural Networks. Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS’19, New York, NY, USA.10.1145/3297858.3304051 ↗
6. Wallach, H., Larochelle, H., Beygelzimer, A., d’Alché-Buc, F., Fox, E., and Garnett, R. (2019). Advances in Neural Information Processing Systems, Curran Associates, Inc.
7. Spread-Transform Dither Modulation Watermarking of Deep Neural Network
8. Chen, H., Rouhani, B.D., Fu, C., Zhao, J., and Koushanfar, F. (2019, January 10–13). DeepMarks: A Secure Fingerprinting Framework for Digital Rights Management of Deep Learning Models. Proceedings of the 2019 on International Conference on Multimedia Retrieval, ICMR’19, New York, NY, USA.10.1145/3323873.3325042 ↗
9. Wang, T., and Kerschbaum, F. (2021, January 19–23). RIGA: Covert and Robust White-Box Watermarking of Deep Neural Networks. Proceedings of the Web Conference 2021, WWW’21, New York, NY, USA.10.1145/3442381.3450000 ↗
10. Tartaglione, E., Grangetto, M., Cavagnino, D., and Botta, M. (2021, January 10–15). Delving in the loss landscape to embed robust watermarks into neural networks. Proceedings of the 2020 25th International Conference on Pattern Recognition (ICPR), Milan, Italy.10.1109/ICPR48806.2021.9413062 ↗
11. Szyller, S., Atli, B.G., Marchal, S., and Asokan, N. (2021, January 20–24). DAWN: Dynamic Adversarial Watermarking of Neural Networks. Proceedings of the 29th ACM International Conference on Multimedia, MM’21, New York, NY, USA.10.1145/3474085.3475591 ↗
12. Adi, Y., Baum, C., Cisse, M., Pinkas, B., and Keshet, J. (2018, January 15–17). Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring. Proceedings of the 27th USENIX Security Symposium (USENIX Security 18), Baltimore, MD, USA.
13. Chen, H., Rouhani, B.D., and Koushanfar, F. (2019). BlackMarks: Blackbox Multibit Watermarking for Deep Neural Networks. arXiv.
14. Guo, J., and Potkonjak, M. (2021). Evolutionary Trigger Set Generation for DNN Black-Box Watermarking. arXiv.
15. PLMmark: A Secure and Robust Black-Box Watermarking Framework for Pre-trained Language Models
16. Deep fidelity in DNN watermarking: A study of backdoor watermarking for classification models10.1016/j.patcog.2023.109844 ↗
17. Watermarking Neural Networks With Watermarked Images10.1109/TCSVT.2020.3030671 ↗
18. Model Watermarking for Image Processing Networks
19. Deep Model Intellectual Property Protection via Deep Watermarking
20. Zhai, G., Zhou, J., Yang, H., Yang, X., An, P., and Wang, J. (2022, January 8–9). Generative Model Watermarking Based on Human Visual System. Proceedings of the Digital Multimedia Communications, Shanghai, China.
21. UDH: Universal Deep Hiding for Steganography, Watermarking, and Light Field Messaging
22. Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R. (2017). Advances in Neural Information Processing Systems, Curran Associates, Inc.
23. Frank, J., Eisenhofer, T., Schönherr, L., Fischer, A., Kolossa, D., and Holz, T. (2020, January 13–18). Leveraging Frequency Analysis for Deep Fake Image Recognition. Proceedings of the 37th International Conference on Machine Learning, Virtual.
24. Zeng, Y., Park, W., Mao, Z.M., and Jia, R. (2021, January 10–17). Rethinking the Backdoor Attacks’ Triggers: A Frequency Perspective. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.10.1109/ICCV48922.2021.01616 ↗
25. Guo, J., and Potkonjak, M. (2018, January 5–8). Watermarking Deep Neural Networks for Embedded Systems. Proceedings of the 2018 IEEE/ACM International Conference on Computer-Aided Design (ICCAD), San Diego, CA, USA.10.1145/3240765.3240862 ↗
26. Li, H., Wenger, E., Shan, S., Zhao, B.Y., and Zheng, H. (2020). Piracy Resistant Watermarks for Deep Neural Networks. arXiv.
27. (2022, December 01). Danbooru2019: A large-Scale Crowdsourced and Tagged Anime Illustration Dataset. Available online: https://gwern.net/danbooru2021#danbooru2019.
28. Yang, W., Tan, R.T., Feng, J., Liu, J., Guo, Z., and Yan, S. (2017, January 21–26). Deep Joint Rain Detection and Removal from a Single Image. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.183 ↗
29. Lata, K., Dave, M., and Nishanth, K.N. (2019, January 12–14). Image-to-Image Translation Using Generative Adversarial Network. Proceedings of the 2019 3rd International conference on Electronics, Communication and Aerospace Technology (ICECA), Coimbatore, India.10.1109/ICECA.2019.8822195 ↗
30. Color and spatial structure in natural scenes10.1364/AO.26.000157 ↗
31. Amplitude spectra of natural images10.1111/j.1475-1313.1992.tb00296.x ↗
32. Deconvolution and Checkerboard Artifacts10.23915/distill.00003 ↗
33. Hiding data hiding10.1016/j.patrec.2022.12.008 ↗
34. Zhu, J.Y., Park, T., Isola, P., and Efros, A.A. (2017, January 22–29). Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.244 ↗
35. Zhang, R., Isola, P., Efros, A.A., Shechtman, E., and Wang, O. (2018, January 18–23). The Unreasonable Effectiveness of Deep Features as a Perceptual Metric. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00068 ↗
36. He, Y., and Hu, Y. (2018, January 25–27). A Proposed Digital Image Watermarking Based on DWT-DCT-SVD. Proceedings of the 2018 2nd IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC), Xi’an, China.10.1109/IMCEC.2018.8469626 ↗