An Audio Watermarking Algorithm Based on Adversarial Perturbation
Source abstract
Abstract
Recently, deep learning has been gradually applied to digital watermarking, which avoids the trouble of hand-designing robust transforms in traditional algorithms. However, most of the existing deep watermarking algorithms use encoder–decoder architecture, which is redundant. This paper proposes a novel audio watermarking algorithm based on adversarial perturbation, AAW. It adds tiny, imperceptible perturbations to the host audio and extracts the watermark with a pre-trained decoder. Moreover, the AAW algorithm also uses an attack simulation layer and a whitening layer to improve performance. The AAW algorithm contains only a differentiable decoder, so it reduces the redundancy. The experimental results also demonstrate that the proposed algorithm is effective and performs better than existing audio watermarking algorithms.
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 Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China
Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, China
Funding
National Key R&D Program of China · the Key R&D Program of Shanxi
References (62)
Show source-provided references
1. Generative artificial intelligence in the metaverse era10.1016/j.cogr.2023.06.001 ↗
2. Xu, D., Fan, S., and Kankanhalli, M. (November, January 29). Combating misinformation in the era of generative AI models. Proceedings of the The ACM International Conference on Multimedia, Ottawa, ON, Canada.
3. Twenty years of digital audio watermarking—A comprehensive review10.1016/j.sigpro.2016.04.005 ↗
4. A comprehensive survey on robust image watermarking10.1016/j.neucom.2022.02.083 ↗
5. An overview of digital video watermarking10.1109/TCSVT.2017.2712162 ↗
6. Screen-shooting resilient watermarking10.1109/TIFS.2018.2878541 ↗
7. Screen-shooting resistant image watermarking based on lightweight neural network in frequency domain10.1016/j.jvcir.2023.103837 ↗
8. RFPS: A robust feature points detection of audio watermarking for against desynchronization attacks in cyber security10.1109/ACCESS.2020.2984283 ↗
9. DeAR: A deep-learning-based audio re-recording resilient watermarking
10. Luo, X., Li, Y., Chang, H., Liu, C., Milanfar, P., and Yang, F. (2023). DVMark: A deep multiscale framework for video watermarking. IEEE Trans. Image Process.10.1109/TIP.2023.3251737 ↗
11. An audio watermark designed for efficient and robust resynchronization after analog playback10.1109/TIFS.2017.2661724 ↗
12. Spread Spectrum Audio Watermarking Using Multiple Orthogonal PN Sequences and Variable Embedding Strengths and Polarities10.1109/TASLP.2017.2782487 ↗
13. Wu, S., Huang, Y., Guan, H., Zhang, S., and Liu, J. (2022). ECSS: High-Embedding-Capacity Audio Watermarking with Diversity Reception. Entropy, 24.10.3390/e24121843 ↗
14. Desynchronization attacks resilient watermarking method based on frequency singular value coefficient modification10.1109/TASLP.2021.3092555 ↗
15. Efficiently self-synchronized audio watermarking for assured audio data transmission10.1109/TBC.2004.838265 ↗
16. A robust, digital-audio watermarking method10.1109/MMUL.2009.44 ↗
17. Localized audio watermarking technique robust against time-scale modification10.1109/TMM.2005.861291 ↗
18. Zhu, J., Kaplan, R., Johnson, J., and Fei-Fei, L. (2018, January 8–14). Hidden: Hiding data with deep networks. Proceedings of the European Conference on Computer Vision, Munich, Germany.10.1007/978-3-030-01267-0_40 ↗
19. Liu, Y., Guo, M., Zhang, J., Zhu, Y., and Xie, X. (2019, January 8–14). A novel two-stage separable deep learning framework for practical blind watermarking. Proceedings of the ACM International Conference on Multimedia, Munich, Germany.10.1145/3343031.3351025 ↗
20. Jia, Z., Fang, H., and Zhang, W. (2021, January 20–24). Mbrs: Enhancing robustness of dnn-based watermarking by mini-batch of real and simulated jpeg compression. Proceedings of the ACM International Conference on Multimedia, Chengdu, China.10.1145/3474085.3475324 ↗
21. Luo, X., Zhan, R., Chang, H., Yang, F., and Milanfar, P. (2020, January 13–19). Distortion agnostic deep watermarking. Proceedings of the IEEE/CVF Computer Vision and Pattern Recognition Conference, Seattle, WA, USA.10.1109/CVPR42600.2020.01356 ↗
22. Zhang, H., Wang, H., Li, Y., Cao, Y., and Shen, C. (2020). Robust watermarking using inverse gradient attention. arXiv.
23. Yu, C. (2020, January 7–12). Attention based data hiding with generative adversarial networks. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA.
24. ReDMark: Framework for residual diffusion watermarking based on deep networks10.1016/j.eswa.2019.113157 ↗
25. Robust audio watermarking in the time domain10.1109/6046.923822 ↗
26. SVD-based adaptive QIM watermarking on stereo audio signals10.1109/TMM.2017.2721642 ↗
27. Wang, S., Yuan, W., Zhang, Z., Wang, J., and Unoki, M. (2021, January 6–11). Synchronous Multi-Bit Audio Watermarking Based on Phase Shifting. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Toronto, ON, Canada.10.1109/ICASSP39728.2021.9414307 ↗
28. Secure Spread Spectrum Watermarking for Multimedia10.1109/83.650120 ↗
29. Quantization index modulation: A class of provably good methods for digital watermarking and information embedding10.1109/18.923725 ↗
30. SNR-constrained heuristics for optimizing the scaling parameter of robust audio watermarking10.1109/TMM.2018.2812599 ↗
31. M-Sequences and Sliding Window Based Audio Watermarking Robust Against Large-Scale Cropping Attacks10.1109/TIFS.2023.3236456 ↗
32. Tavakoli, A., Honjani, Z., and Sajedi, H. (2022). Convolutional Neural Network-Based Image Watermarking using Discrete Wavelet Transform. arXiv.10.1007/s41870-023-01232-8 ↗
33. Vukotić, V., Chappelier, V., and Furon, T. (2020). Are classification deep neural networks good for blind image watermarking?. Entropy, 22.10.3390/e22020198 ↗
34. Fernandez, P., Sablayrolles, A., Furon, T., Jégou, H., and Douze, M. (2022, January 23–27). Watermarking Images in Self-Supervised Latent Spaces. Proceedings of the International Conference on Acoustics, Speech, and Signal Processing, Singapore.10.1109/ICASSP43922.2022.9746058 ↗
35. Caron, M., Touvron, H., Misra, I., Jégou, H., Mairal, J., Bojanowski, P., and Joulin, A. (2021, January 11–17). Emerging properties in self-supervised vision transformers. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, BC, Canada.10.1109/ICCV48922.2021.00951 ↗
36. Jia, X., Wei, X., Cao, X., and Han, X. (2020, January 12–16). Adv-watermark: A Novel Watermark Perturbation for Adversarial Examples. Proceedings of the 28th ACM International Conference on Multimedia, Seattle, WA, USA.10.1145/3394171.3413976 ↗
37. Ghamizi, S., Cordy, M., Papadakis, M., and Traon, Y.L. (2021, January 2–9). Evasion Attack STeganography: Turning Vulnerability of Machine Learning to Adversarial Attacks into a Real-World Application. Proceedings of the AAAI Conference on Artificial Intelligence, Philadelphia, PA, USA.10.1109/ICCVW54120.2021.00010 ↗
38. Kong, Y., and Zhang, J. (2020, January 25–29). Adversarial Audio: A New Information Hiding Method. Proceedings of the INTERSPEECH, Shanghai, China.10.21437/Interspeech.2020-1294 ↗
39. Goodfellow, I.J., Shlens, J., and Szegedy, C. (2014). Explaining and harnessing adversarial examples. arXiv.
40. Moosavi-Dezfooli, S.M., Fawzi, A., and Frossard, P. (2016, January 27–30). Deepfool: A simple and accurate method to fool deep neural networks. Proceedings of the IEEE/CVF Computer Vision and Pattern Recognition Conference, Las Vegas, NV, USA.10.1109/CVPR.2016.282 ↗
41. Dong, Y., Liao, F., Pang, T., Su, H., Zhu, J., Hu, X., and Li, J. (2018, January 18–23). Boosting adversarial attacks with momentum. Proceedings of the IEEE/CVF Computer Vision and Pattern Recognition Conference, Salt Lake City, UT, USA.10.1109/CVPR.2018.00957 ↗
42. Adversarial deep learning: A survey on adversarial attacks and defense mechanisms on image classification10.1109/ACCESS.2022.3208131 ↗
43. Adversarial machine learning in image classification: A survey toward the defender’s perspective10.1145/3485133 ↗
44. Peng, B., Peng, B., Yong, S., and Liu, L. (2022). An empirical study of fully black-box and universal adversarial attack for SAR target recognition. Remote Sens., 14.10.3390/rs14164017 ↗
45. Scattering model guided adversarial examples for SAR target recognition: Attack and defense
46. Carlini, N., and Wagner, D. (2018, January 24). Audio adversarial examples: Targeted attacks on speech-to-text. Proceedings of the 2018 IEEE security and privacy workshops (SPW), San Francisco, CA, USA.10.1109/SPW.2018.00009 ↗
47. Selective audio adversarial example in evasion attack on speech recognition system10.1109/TIFS.2019.2925452 ↗
48. Audio adversarial detection through classification score on speech recognition systems10.1016/j.cose.2022.103061 ↗
49. Zhang, Y., Hu, S., Zhang, L.Y., Shi, J., Li, M., Liu, X., and Jin, H. (2024, January 20–22). Why does little robustness help? a further step towards understanding adversarial transferability. Proceedings of the 45th IEEE Symposium on Security and Privacy (S&P’24), San Francisco, CA, USA.
50. 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 IEEE/CVF Computer Vision and Pattern Recognition Conference, Salt Lake City, UT, USA.10.1109/CVPR.2018.00068 ↗
51. Noh, H., Araujo, A., Sim, J., Weyand, T., and Han, B. (2017, January 22–29). Large-scale image retrieval with attentive deep local features. Proceedings of the IEEE/CVF International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.374 ↗
52. Babenko, A., Slesarev, A., Chigorin, A., and Lempitsky, V. (2014, January 6–12). Neural codes for image retrieval. Proceedings of the European Conference on Computer Vision, Zurich, Switzerland.10.1007/978-3-319-10590-1_38 ↗
53. Oord, A.v.d., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A., and Kavukcuoglu, K. (2016). Wavenet: A generative model for raw audio. arXiv.
54. Crosstransformers: Spatially-aware few-shot transfer
55. Spijkervet, J., and Burgoyne, J.A. (2021). Contrastive learning of musical representations. arXiv.
56. Sohn, K. (2016). Improved deep metric learning with multi-class n-pair loss objective. Adv. Neural Inf. Process. Syst., 29.
57. Chen, T., Kornblith, S., Norouzi, M., and Hinton, G. (2020, January 13–18). A simple framework for contrastive learning of visual representations. Proceedings of the International Conference on Machine Learning, PMLR, Virtual.
58. Jégou, H., and Chum, O. (2012). Negative evidences and co-occurences in image retrieval: The benefit of PCA and whitening. The European Conference on Computer Vision, Springer.10.1007/978-3-642-33709-3_55 ↗
59. Evaluation of objective quality measures for speech enhancement10.1109/TASL.2007.911054 ↗
60. Defferrard, M., Benzi, K., Vandergheynst, P., and Bresson, X. (2017, January 23–28). FMA: A Dataset for Music Analysis. Proceedings of the International Society for Music Information Retrieval Conference, Suzhou, China.
61. Kingma, D.P., and Ba, J. (2015, January 7–9). Adam: A Method for Stochastic Optimization. Proceedings of the International Conference on Learning Representations, San Diego, CA, USA.
62. Scheibler, R., Bezzam, E., and Dokmanić, I. (2018, January 15–20). Pyroomacoustics: A Python Package for Audio Room Simulation and Array Processing Algorithms. Proceedings of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, Canada.10.1109/ICASSP.2018.8461310 ↗