Semi-Supervised Deep Domain Adaptation for Deepfake Detection
Semi-Supervised Deep Domain Adaptation for Deepfake Detection
复制标题
DOI：
10.1109/wacvw60836.2024.00116
复制
发表时间：
2024-01
期刊：
影响因子：
--
通讯作者：
Md Shamim Seraj;Ankita Singh;Shayok Chakraborty
中科院分区：
文献类型：
--
作者：
Md Shamim Seraj;Ankita Singh;Shayok Chakraborty
随着生成模型（如GAN）的出现和普及，合成图像生成和操纵已变得司空见惯。这促进了有效的深度伪造检测技术的积极研究。虽然现有的检测技术已经证明了前景，但当对使用不同伪造技术生成的数据进行测试时，它们的性能会受到影响，而模型还没有得到充分的训练。在不丢失关于深度伪造的先验知识（灾难性遗忘）的情况下检测新型深度伪造的挑战在当今世界至关重要。在本文中，我们提出了一种新的深度域自适应框架来解决深度伪造检测研究中的这一重要问题。我们的框架可以利用使用特定伪造技术（源域）生成的大量标记数据（假/真）和使用不同伪造技术（目标域）生成的少量标记数据来诱导在源域和目标域上具有良好泛化能力的深度神经网络。此外，深度神经网络是数据饥渴型的，需要大量的标记训练数据，这些数据在deepfake检测的背景下可能并不总是可用的;我们的框架还可以有效地利用目标域中的未标记数据，这些数据比标记数据更容易获得。我们设计了一个新的损失函数，并使用随机梯度下降（SGD）方法来优化损失并训练深度网络。我们对基准FaceForensics+ +数据集进行了广泛的实证研究，使用了三种类型的deepfake，证实了我们框架相对于竞争基线的承诺和潜力。
With the advent and popularity of generative models such as GANs, synthetic image generation and manipu-lation has become commonplace. This has promoted active research in the development of effective deepfake de-tection technology. While existing detection techniques have demonstrated promise, their performance suffers when tested on data generated using a different faking technology, on which the model has not been sufficiently trained. This challenge of detecting new types of deepfakes, without losing its prior knowledge about deepfakes (catastrophic for-getting), is of utmost importance in today’ s world. In this paper, we propose a novel deep domain adaptation frame-work to address this important problem in deepfake detection research. Our framework can leverage a large amount of labeled data (fake / genuine) generated using a particu-lar faking technique (source domain) and a small amount of labeled data generated using a different faking technique (target domain) to induce a deep neural network with good generalization capability on both the source and the target domains. Further, deep neural networks are data-hungry and require a large amount of labeled training data, which may not always be available in the context of deepfake de-tection; our framework can also efficiently utilize unlabeled data in the target domain, which is more readily available than labeled data. We design a novel loss function and use the stochastic gradient descent (SGD) method to optimize the loss and train the deep network. Our extensive empiri-cal studies on the benchmark FaceForensics+ + dataset, using three types of deepfakes, corroborate the promise and potential of our framework against competing baselines.