期刊
IEEE MULTIMEDIA
卷 30, 期 1, 页码 28-35出版社
IEEE COMPUTER SOC
DOI: 10.1109/MMUL.2022.3213004
关键词
Watermarking; Copyright protection; Generators; Robustness; Data models; Visualization; Generative adversarial networks; Digital images; CGAN; Robust Watermarking; Attack; Deep Learning
This research designs an effective image watermarking attack method based on the conditional generative adversarial nets (CGAN). It constructs a targeted and combined loss function according to the network structure of CGAN, which can ensure an acceptable visual quality of attacked image and make the watermark extraction fail simultaneously. Experimental results demonstrate the effectiveness of this method for some state-of-the-art deep robust image watermarking methods with transferability. As an attack method, it can serve as an evaluation standard to measure the robustness of watermarking.
Robust watermarking plays an essential role in copyright protection for digital images. Meanwhile, the studies of robust image watermarking and corresponding attack methods promote and complement each other. Because the traditional attack methods are weak to attack the deep watermarking, in this work, we thus design an effective watermarking attack method based on the conditional generative adversarial nets (CGAN). Also, according to the network structure of CGAN, a targeted and combined loss function is constructed, which can guarantee an acceptable visual quality of attacked image and make the watermark extraction fail simultaneously. Experimental results demonstrate that our method is effective for some state-of-the-art deep robust image watermarking methods with the transferability. In addition, as an attack method, it can be regarded as an evaluation standard to measure the robustness of watermarking.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据