GAN-generated face anti-forensics based on image wavelet domain adaptive perturbation
Aiming at the insufficient attack transferability of existing generative adversarial network(GAN)-generated face anti-forensics methods,a GAN-generated face anti-forensics method based on image wavelet domain adaptive perturbations is proposed to improve the attack transferability.The proposed method resists the forensic models by adding perturbations to the wavelet domain information of GAN-generated facial ima-ges,which are the frequency components after the image wavelet decomposition.Furthermore,adaptive per-turbation thresholds are designed based on just noticeable distortion(JND)in both the spatial and frequency domains,setting different perturbation strengths for different pixel positions in the image,and thereby enhan-cing the imperceptibility of the perturbations to the human eyes.In addition,a data argumentation approach is designed to expand the distribution diversity of the anti-forensics image,thereby further improving the attack transferability.Experimental results show that compared with the six baseline methods,the anti-forensics im-age generated by the proposed method can achieve stronger attack transferability while ensuring the perturba-tion imperceptibility to the human eyes.
万方数据
维普
