NAA-GAN: Noise-Aware Cross-Attention for Robust Blind Image Watermarking

Authors

  • Surni Erniwati Universitas Nusa Mandiri
  • Jufriadif Na'am Universitas Nusa Mandiri
  • Ferda Ernawan Universiti Malaysia Pahang Al-Sultan Abdullah

DOI:

https://doi.org/10.62411/jcta.17836

Keywords:

Blind image watermarking, Copyright protection, Cross-attention, Deep learning, Distortion-conditioned embedding, Generative adversarial network, Noise-aware attention, Robust watermarking

Abstract

Robust blind image watermarking remains challenging because embedded watermark information must remain recoverable after image processing while preserving the visual quality of the watermarked image. This paper proposes NAA-GAN, a generative adversarial watermarking framework that conditions the encoder on a six-dimensional descriptor of the anticipated distortion category. The encoder integrates dense feature aggregation, noise-aware cross-attention, and residual embedding to insert a 30-bit watermark. During training, a noise subnetwork simulates image processing attacks, while the decoder recovers the watermark from the received image without requiring the distortion descriptor. Experiments on COCO, PASCAL VOC2012, ImageNet, and EUVP assess image fidelity using peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM), and robustness using bit accuracy (BA). NAA-GAN achieves PSNR values ranging from 36.96 to 37.79 dB and average BAs above 98% across the four datasets under the five evaluated attacks. On COCO, it achieves 99.02% BA under JPEG compression and an average BA of 92.59% across distortions not encountered during training. An ablation study shows that removing the distortion descriptor reduces COCO PSNR from 37.38 to 36.73 dB and average BA from 98.07% to 96.14%. Across all four datasets, NAA-GAN achieves higher PSNR and JPEG BA than the compared models. However, ARWGAN-CN achieves higher SSIM and average BA, indicating that the proposed method improves pixel-level fidelity and JPEG robustness but does not consistently outperform competing methods across all evaluation metrics.

Author Biographies

Surni Erniwati, Universitas Nusa Mandiri

Informatics Doctoral Program, Universitas Nusa Mandiri, Jakarta 13620, Indonesia; Department of Informatics Engineering, Universitas Teknologi Mataram, Mataram 83116, Indonesia

Jufriadif Na'am, Universitas Nusa Mandiri

Informatics Doctoral Program, Universitas Nusa Mandiri, Jakarta 13620, Indonesia

Ferda Ernawan, Universiti Malaysia Pahang Al-Sultan Abdullah

Computing Program, Universiti Malaysia Pahang Al-Sultan Abdullah, Pekan, Pahang 26600, Malaysia; Informatics Doctoral Program, Universitas Nusa Mandiri, Jakarta 13620, Indonesia

References

J. Huang, T. Luo, L. Li, G. Yang, H. Xu, and C.-C. Chang, “ARWGAN: Attention-Guided Robust Image Watermarking Model Based on GAN,” IEEE Trans. Instrum. Meas., vol. 72, pp. 1–17, 2023, doi: 10.1109/TIM.2023.3285981.

L. Xiong, X. Han, C.-N. Yang, and Y.-Q. Shi, “Robust Reversible Watermarking in Encrypted Image With Secure Multi-Party Based on Lightweight Cryptography,” IEEE Trans. Circuits Syst. Video Technol., vol. 32, no. 1, pp. 75–91, Jan. 2022, doi: 10.1109/TCSVT.2021.3055072.

I. C. Dragoi and D. Coltuc, “On the Security of Reversible Data Hiding in Encrypted Images by MSB Prediction,” IEEE Trans. Inf. Forensics Secur., vol. 16, pp. 187–189, 2021, doi: 10.1109/TIFS.2020.3006382.

L.-C. Kuo and C.-C. Tai, “Robust Image-Based Water-Level Estimation Using Single-Camera Monitoring,” IEEE Trans. Instrum. Meas., vol. 71, pp. 1–11, 2022, doi: 10.1109/TIM.2022.3161691.

J. Molina-Garcia, B. P. Garcia-Salgado, V. Ponomaryov, R. Reyes-Reyes, S. Sadovnychiy, and C. Cruz-Ramos, “An effective fragile watermarking scheme for color image tampering detection and self-recovery,” Signal Process. Image Commun., vol. 81, no. October 2019, p. 115725, Feb. 2020, doi: 10.1016/j.image.2019.115725.

P. Lefèvre, P. Carré, C. Fontaine, P. Gaborit, and J. Huang, “Efficient image tampering localization using semi-fragile watermarking and error control codes,” Signal Processing, vol. 190, p. 108342, Jan. 2022, doi: 10.1016/j.sigpro.2021.108342.

X. Wang, X. Li, and Q. Pei, “Independent Embedding Domain Based Two-Stage Robust Reversible Watermarking,” IEEE Trans. Circuits Syst. Video Technol., vol. 30, no. 8, pp. 2406–2417, Aug. 2020, doi: 10.1109/TCSVT.2019.2915116.

A. Winarno, D. R. I. M. Setiadi, A. A. Arrasyid, C. A. Sari, and E. H. Rachmawanto, “Image watermarking using low wavelet subband based on 8×8 sub-block DCT,” in 2017 International Seminar on Application for Technology of Information and Communication (iSemantic), Oct. 2017, pp. 11–15. doi: 10.1109/ISEMANTIC.2017.8251835.

T. Jin and W. Zhang, “A Novel Interpolated DFT Synchrophasor Estimation Algorithm With an Optimized Combined Cosine Self-Convolution Window,” IEEE Trans. Instrum. Meas., vol. 70, pp. 1–10, 2021, doi: 10.1109/TIM.2020.3033073.

S. Shi, T. Luo, J. Huang, and M. Du, “A Novel HDR Image Zero-Watermarking Based on Shift-Invariant Shearlet Transform,” Secur. Commun. Networks, vol. 2021, pp. 1–12, Mar. 2021, doi: 10.1155/2021/6662700.

H. J. Ko, C. T. Huang, G. Horng, and S. J. WANG, “Robust and blind image watermarking in DCT domain using inter-block coefficient correlation,” Inf. Sci. (Ny)., vol. 517, pp. 128–147, 2020, doi: 10.1016/j.ins.2019.11.005.

H. T. Hu, L. Y. Hsu, and H. H. Chou, “An improved SVD-based blind color image watermarking algorithm with mixed modulation incorporated,” Inf. Sci. (Ny)., vol. 519, pp. 161–182, May 2020, doi: 10.1016/j.ins.2020.01.019.

C. Zhou et al., “A New Model Transfer Strategy Among Spectrometers Based on SVR Parameter Calibrating,” IEEE Trans. Instrum. Meas., vol. 70, pp. 1–13, 2021, doi: 10.1109/TIM.2021.3119129.

C. Yang, P. An, and L. Shen, “Blind Image Quality Measurement via Data-Driven Transform-Based Feature Enhancement,” IEEE Trans. Instrum. Meas., vol. 71, pp. 1–12, 2022, doi: 10.1109/TIM.2022.3191661.

A. Lin, B. Chen, J. Xu, Z. Zhang, G. Lu, and D. Zhang, “DS-TransUNet: Dual Swin Transformer U-Net for Medical Image Segmentation,” IEEE Trans. Instrum. Meas., vol. 71, pp. 1–15, 2022, doi: 10.1109/TIM.2022.3178991.

B. Chen, Z. Zhang, Y. Li, G. Lu, and D. Zhang, “Multi-Label Chest X-Ray Image Classification via Semantic Similarity Graph Embedding,” IEEE Trans. Circuits Syst. Video Technol., vol. 32, no. 4, pp. 2455–2468, Apr. 2022, doi: 10.1109/TCSVT.2021.3079900.

X. Luo, R. Zhan, H. Chang, F. Yang, and P. Milanfar, “Distortion Agnostic Deep Watermarking,” in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2020, pp. 13545–13554. doi: 10.1109/CVPR42600.2020.01356.

Z. Huang, J. Zhang, Y. Zhang, and H. Shan, “DU-GAN: Generative Adversarial Networks With Dual-Domain U-Net-Based Discriminators for Low-Dose CT Denoising,” IEEE Trans. Instrum. Meas., vol. 71, pp. 1–12, 2022, doi: 10.1109/TIM.2021.3128703.

J. Zhu, R. Kaplan, J. Johnson, and L. Fei-Fei, “HiDDeN: Hiding Data With Deep Networks,” in Computer Vision – ECCV 2018, 2018, pp. 682–697. doi: 10.1007/978-3-030-01267-0_40.

K. Hao, G. Feng, and X. Zhang, “Robust image watermarking based on generative adversarial network,” China Commun., vol. 17, no. 11, pp. 131–140, Nov. 2020, doi: 10.23919/JCC.2020.11.012.

Z. Jia, H. Fang, and W. Zhang, “MBRS: Enhancing Robustness of DNN-based Watermarking by Mini-Batch of Real and Simulated JPEG Compression,” in Proceedings of the 29th ACM International Conference on Multimedia, Oct. 2021, pp. 41–49. doi: 10.1145/3474085.3475324.

H. Chen and L. Zhang, “A Novel Digital watermarking Approach under the DCT and SVM,” in 2021 IEEE 4th International Conference on Automation, Electronics and Electrical Engineering (AUTEEE), Nov. 2021, pp. 154–156. doi: 10.1109/AUTEEE52864.2021.9668682.

M. Ahmadi, A. Norouzi, N. Karimi, S. Samavi, and A. Emami, “ReDMark: Framework for residual diffusion watermarking based on deep networks,” Expert Syst. Appl., vol. 146, p. 113157, May 2020, doi: 10.1016/j.eswa.2019.113157.

P. Fernandez, A. Sablayrolles, T. Furon, H. Jegou, and M. Douze, “Watermarking Images in Self-Supervised Latent Spaces,” in ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2022, pp. 3054–3058. doi: 10.1109/ICASSP43922.2022.9746058.

G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely Connected Convolutional Networks,” in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jul. 2017, pp. 2261–2269. doi: 10.1109/CVPR.2017.243.

Z. Wu, J. Hai, L. Zhang, J. Chen, G. Cheng, and B. Yan, “Cascaded Fully Convolutional DenseNet for Automatic Kidney Segmentation in Ultrasound Images,” in 2019 2nd International Conference on Artificial Intelligence and Big Data (ICAIBD), May 2019, pp. 384–388. doi: 10.1109/ICAIBD.2019.8836994.

C.-F. R. Chen, Q. Fan, and R. Panda, “CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification,” in 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Oct. 2021, pp. 347–356. doi: 10.1109/ICCV48922.2021.00041.

B. Chen, W. Tan, G. Coatrieux, Y. Zheng, and Y.-Q. Shi, “A Serial Image Copy-Move Forgery Localization Scheme With Source/Target Distinguishment,” IEEE Trans. Multimed., vol. 23, pp. 3506–3517, 2021, doi: 10.1109/TMM.2020.3026868.

C. Yu, “Attention Based Data Hiding with Generative Adversarial Networks,” Proc. AAAI Conf. Artif. Intell., vol. 34, no. 01, pp. 1120–1128, Apr. 2020, doi: 10.1609/aaai.v34i01.5463.

H. Zhang, H. Wang, Y. Cao, C. Shen, and Y. Li, “Robust Data Hiding Using Inverse Gradient Attention,” Arxiv preprint. Oct. 17, 2022. [Online]. Available: http://arxiv.org/abs/2011.10850

K. A. Zhang, L. Xu, A. Cuesta-Infante, and K. Veeramachaneni, “Robust Invisible Video Watermarking with Attention,” Arxiv preprint. Sep. 03, 2019. doi: 10.48550/arXiv.1909.01285.

T.-Y. Lin et al., “Microsoft COCO: Common Objects in Context,” in Computer Vision – ECCV 2014, 2014, pp. 740–755. doi: 10.1007/978-3-319-10602-1_48.

M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman, “The Pascal Visual Object Classes (VOC) Challenge,” Int. J. Comput. Vis., vol. 88, no. 2, pp. 303–338, Jun. 2010, doi: 10.1007/s11263-009-0275-4.

J. Deng, W. Dong, R. Socher, L.-J. Li, Kai Li, and Li Fei-Fei, “ImageNet: A large-scale hierarchical image database,” in 2009 IEEE Conference on Computer Vision and Pattern Recognition, Jun. 2009, pp. 248–255. doi: 10.1109/CVPR.2009.5206848.

M. J. Islam, Y. Xia, and J. Sattar, “Fast Underwater Image Enhancement for Improved Visual Perception,” IEEE Robot. Autom. Lett., vol. 5, no. 2, pp. 3227–3234, Apr. 2020, doi: 10.1109/LRA.2020.2974710.

Y. Liu, M. Guo, J. Zhang, Y. Zhu, and X. Xie, “A Novel Two-stage Separable Deep Learning Framework for Practical Blind Watermarking,” in Proceedings of the 27th ACM International Conference on Multimedia, Oct. 2019, pp. 1509–1517. doi: 10.1145/3343031.3351025.

Downloads

Published

2026-10-25

How to Cite

Erniwati, S., Na’am, J., & Ernawan, F. (2026). NAA-GAN: Noise-Aware Cross-Attention for Robust Blind Image Watermarking. Journal of Computing Theories and Applications, 4(2), 605–622. https://doi.org/10.62411/jcta.17836