基于改进CycleGAN的人脸性别伪造图像生成模型  

Generation Model of Gender-forged Face Image Based on Improved CycleGAN

作　　者：石达 芦天亮[1] 杜彦辉[1] 张建岭 暴雨轩 SHI Da;LU Tian-liang;DU Yan-hui;ZHANG Jian-ling;BAO Yu-xuan(College of Information and Cyber Security,People's Public Security University of China,Beijing 100038,China)

机构地区：[1]中国人民公安大学信息网络安全学院,北京100038

出　　处：《计算机科学》2022年第2期31-39,共9页Computer Science

基　　金：国家重点研发计划(2017YFB0802804);中国人民公安大学2020年基本科研业务费重大项目(2020JKF101)。

摘　　要：深度伪造可以将人的声音、面部及身体动作拼接,从而合成虚假内容,用于转换性别、改变年龄等。基于生成对抗式图像翻译网络的人脸性别伪造图像存在容易改变无关图像域、人脸细节不够丰富等问题。针对这些问题,文中提出基于改进CycleGAN的人脸性别伪造图像生成模型。首先,优化生成器结构,利用注意力机制与自适应残差块提取更丰富的人脸特征;然后,借鉴相对损失的思想对损失函数进行改进,提高判别器的判别能力。最后,提出基于年龄约束的模型训练策略,减小了年龄变化对生成图像的影响。在CelebA和IMDB-WIKI数据集上进行实验,实验结果表明,与原始CycleGAN方法和UGATIT方法相比,所提方法能够生成更加真实的人脸性别伪造图像,伪造男性和伪造女性的平均内容准确率分别为82.65%和78.83%,FID平均得分分别为32.14和34.50。Deepfake can be used to combine human voices,faces and body movements into fake content,switch gender and change age,etc.There are some problems of gender-forged face images based on generative adversarial image translation networks such as the irrelevant image domain changes easily and insufficient face details in generated images.To solve these problems,an gene-ration model of gender-forged face image based on improved CycleGAN is proposed.Firstly,the generator is optimized by using the attention mechanism and adaptive residual blocks to extract richer facial features.Then,with the aim to improve the ability of the discriminator,the loss function is modified by the idea of relative loss.Finally,a model training strategy based on age constraints is proposed to reduce the impact of age changes on the generated images.Performing experiments on the CelebA and IMDB-WIKI datasets,the experimental results show that,compared with the original CycleGAN method and the UGATIT method,the proposed method can generate more real gender-forged face images.The average content accuracy of fake male images and fake female images is 82.65% and 78.83%,and the average FID score is 32.14 and 34.50,respectively.

关 键 词：深度伪造 深度学习 生成对抗网络 图像翻译 图像生成 人脸性别伪造 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]