Images synthesized by powerful generative adversarial network (GAN) based methods have drawn moral and privacy concerns. Although image forensic models have reached great performance in detecting fake images from real ones, these models can be easily fooled with a simple adversarial attack. But, the noise adding adversarial samples are also arousing suspicion. In this paper, instead of adding adversarial noise, we optimally search adversarial points on face manifold to generate anti-forensic fake face images. We iteratively do a gradient-descent with each small step in the latent space of a generative model, e.g. Style-GAN, to find an adversarial latent vector, which is similar to norm-based adversarial attack but in latent space. Then, the generated fake images driven by the adversarial latent vectors with the help of GANs can defeat main-stream forensic models. For examples, they make the accuracy of deepfake detection models based on Xception or EfficientNet drop from over 90% to nearly 0%, meanwhile maintaining high visual quality. In addition, we find manipulating style vector $z$ or noise vectors $n$ at different levels have impacts on attack success rate. The generated adversarial images mainly have facial texture or face attributes changing.
翻译:由强大的基因对抗网络(GAN)所合成的图像合成,已经引起了道德和隐私方面的关注。虽然图像法证模型在从真实图像中探测假图像方面达到了很高的性能,但这些模型很容易被简单的对抗性攻击所愚弄。但是,添加对抗性样品的噪音也令人产生怀疑。在本文中,我们最好在脸部多处搜索对抗性试验点,而不是添加对抗性噪音,以产生抗法假脸部图像。我们迭代地在基因模型(例如Style-GAN)潜伏空间的每一个小步上都使用斜坡度,以寻找一个与标准对抗性攻击相类似的对抗性潜伏性媒介。然后,由对抗性潜伏性媒介驱动的假图像在GANs的帮助下可以击败主流法医学模型。举例来说,它们根据Xception或高效的网络下降率从90%以上跌至近0%,同时保持高视觉质量。此外,我们发现,我们发现操纵时态矢量值为$z$或噪音矢量为$n的表面图像会在不同水平上对攻击率产生影响。