论文标题
黑框攻击对gan生成的图像探测器，并具有对比度扰动
Black-Box Attack against GAN-Generated Image Detector with Contrastive Perturbation
论文作者
论文摘要
视觉上现实的gan生成的面部图像引起了对潜在滥用的明显关注。近年来，已经开发了许多有效的法医算法来检测此类合成图像。评估此类法医检测器针对对抗性攻击的脆弱性很重要。在本文中，我们提出了一种针对GAN生成的图像探测器的新的黑盒攻击方法。采用了一种新颖的对比学习策略来训练基于编码器网络的抗验证模型在对比损失函数下。 GAN图像及其模拟的真实对应物分别构建为正样本和负样本。利用训练的攻击模型，不可察觉的对比扰动可以应用于输入合成图像，以在某种程度上去除GAN指纹。因此，预计现有的GAN生成的图像探测器将被欺骗。广泛的实验结果证明，提议的攻击有效地降低了六个流行gan的三个最先进的探测器的准确性。还实现了攻击图像的高视觉质量。源代码将在https://github.com/zxmmd/battgand上找到。
Visually realistic GAN-generated facial images raise obvious concerns on potential misuse. Many effective forensic algorithms have been developed to detect such synthetic images in recent years. It is significant to assess the vulnerability of such forensic detectors against adversarial attacks. In this paper, we propose a new black-box attack method against GAN-generated image detectors. A novel contrastive learning strategy is adopted to train the encoder-decoder network based anti-forensic model under a contrastive loss function. GAN images and their simulated real counterparts are constructed as positive and negative samples, respectively. Leveraging on the trained attack model, imperceptible contrastive perturbation could be applied to input synthetic images for removing GAN fingerprint to some extent. As such, existing GAN-generated image detectors are expected to be deceived. Extensive experimental results verify that the proposed attack effectively reduces the accuracy of three state-of-the-art detectors on six popular GANs. High visual quality of the attacked images is also achieved. The source code will be available at https://github.com/ZXMMD/BAttGAND.
