Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, 430072, China.
Neural Netw. 2023 Mar;160:216-226. doi: 10.1016/j.neunet.2023.01.001. Epub 2023 Jan 9.
The abuse of deepfakes, a rising face swap technique, causes severe concerns about the authenticity of visual content and the dissemination of misinformation. To alleviate the threats imposed by deepfakes, a vast body of data-centric detectors has been deployed. However, the performance of these methods can be easily defected by degradations on deepfakes. To improve the performance of degradation deepfake detection, we creatively explore the recovery method in the feature space to preserve the artifacts for detection instead of directly in the image domain. In this paper, we propose a method, namely DF-UDetector, against degradation deepfakes by modeling the degraded images and transforming the extracted features to a high-quality level. To be specific, the whole model consists of three key components: an image feature extractor to capture image features, a feature transforming module to map the degradation features into a higher quality, and a discriminator to determine whether the feature map is of high quality enough. Extensive experiments on multiple video datasets show that our proposed model performs comparably or even better than state-of-the-art counterparts. Moreover, DF-UDetector outperforms by a small margin when detecting deepfakes in the wild.
深度伪造技术的滥用引发了人们对视觉内容真实性和错误信息传播的严重担忧。为了减轻深度伪造带来的威胁，人们已经部署了大量基于数据的检测器。然而，这些方法的性能很容易受到深度伪造的降级影响。为了提高降级深度伪造检测的性能，我们创造性地探索了特征空间中的恢复方法，以保留用于检测的伪影，而不是直接在图像域中。在本文中，我们提出了一种名为 DF-UDetector 的方法，通过对降级图像进行建模，并将提取的特征转换到高质量水平，从而对抗降级深度伪造。具体来说，整个模型由三个关键组件组成：图像特征提取器用于捕获图像特征、特征转换模块用于将降级特征映射到更高质量、以及鉴别器用于确定特征图是否足够高质量。在多个视频数据集上的广泛实验表明，我们提出的模型在性能上可与最先进的方法相媲美，甚至更好。此外，DF-UDetector 在检测野外深度伪造时，性能略优。
