EUVIMEDEUVIMED entdecken
Crossref

High-Frequency Matters: Attack and Defense for Image-Processing Model Watermarking

Huajie Chen, Tianqing Zhu, Chi Liu, Shui Yu, Wanlei Zhou

IEEE Transactions on Services Computing · 2024-07 · 17 (4) · 1565-1579

DOI: 10.1109/tsc.2024.3349784 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Services Computing, 2024-07. Verfasst von Huajie Chen und 4 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 35 Literaturangaben. Gefördert von: Australian Research Council Australia.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, there has been significant advancement in the field of model watermarking techniques. However, the protection of image-processing neural networks remains a challenge, with only a limited number of methods being developed. The objective of these techniques is to embed a watermark in the output images of the target generative network, so that the watermark signal can be detected in the output of a surrogate model obtained through model extraction attacks. This promising technique, however, has certain limits. Analysis of the frequency domain reveals that the watermark signal is mainly concealed in the high-frequency components of the output. Thus, we propose an overwriting attack that involves forging another watermark in the output of the generative network. The experimental results demonstrate the efficacy of this attack in sabotaging existing watermarking schemes for image-processing networks with an almost 100% success rate. To counter this attack, we propose an adversarial framework for the watermarking network. The framework incorporates a specially-designed adversarial training step, where the watermarking network is trained to defend against the overwriting network, thereby enhancing its robustness. Additionally, we observe an overfitting phenomenon in the existing watermarking method, which can render it ineffective. To address this issue, we modify the training process to eliminate the overfitting problem.

Förderung

  • Australian Research Council Australia

Zitieren

APA

Chen, H., Zhu, T., Liu, C., Yu, S., & Zhou, W. (2024). High-Frequency Matters: Attack and Defense for Image-Processing Model Watermarking. IEEE Transactions on Services Computing, 17(4), 1565-1579. https://doi.org/10.1109/tsc.2024.3349784

Vancouver

Chen H, Zhu T, Liu C, Yu S, Zhou W. High-Frequency Matters: Attack and Defense for Image-Processing Model Watermarking. IEEE Transactions on Services Computing. 2024;17(4):1565-1579. doi:10.1109/tsc.2024.3349784

BibTeX
@article{Chen2024,
  author = {Chen, Huajie and Zhu, Tianqing and Liu, Chi and Yu, Shui and Zhou, Wanlei},
  title = {High-Frequency Matters: Attack and Defense for Image-Processing Model Watermarking},
  journal = {IEEE Transactions on Services Computing},
  year = {2024},
  volume = {17},
  number = {4},
  pages = {1565--1579},
  doi = {10.1109/tsc.2024.3349784}
}
Kostenlos starten →