Deepfakes pose growing challenges to the trust of information on the Internet. Thus, detecting deepfakes has attracted increasing attentions from both academia and industry. State-of-the-art deepfake detection methods consist of two key components, i.e., face extractor and face classifier, which extract the face region in an image and classify it to be real/fake, respectively. Existing studies mainly focused on improving the detection performance in non-adversarial settings, leaving security of deepfake detection in adversarial settings largely unexplored. In this work, we aim to bridge the gap. In particular, we perform a systematic measurement study to understand the security of the state-of-the-art deepfake detection methods in adversarial settings. We use two large-scale public deepfakes data sources including FaceForensics++ and Facebook Deepfake Detection Challenge, where the deepfakes are fake face images; and we train state-of-the-art deepfake detection methods. These detection methods can achieve 0.94--0.99 accuracies in non-adversarial settings on these datasets. However, our measurement results uncover multiple security limitations of the deepfake detection methods in adversarial settings. First, we find that an attacker can evade a face extractor, i.e., the face extractor fails to extract the correct face regions, via adding small Gaussian noise to its deepfake images. Second, we find that a face classifier trained using deepfakes generated by one method cannot detect deepfakes generated by another method, i.e., an attacker can evade detection via generating deepfakes using a new method. Third, we find that an attacker can leverage backdoor attacks developed by the adversarial machine learning community to evade a face classifier. Our results highlight that deepfake detection should consider the adversarial nature of the problem.
翻译:深假对互联网信息的信任构成越来越多的挑战。 因此, 检测深假对互联网信息的信任构成越来越多的挑战 。 因此, 深假检测已经吸引了学术界和业界越来越多的关注。 最先进的深假检测方法包括两个关键组成部分, 即脸提取器和脸分解器, 分别从图像中提取脸部区域, 并将其分类为真实/ 假的 。 现有研究主要侧重于改进非对称环境中的检测性能, 使得对称环境中的深假发现安全性。 这项工作的目的是弥合差距。 特别是, 我们进行系统化的测量研究, 以了解在对称环境中的状态深假的深假发现法检测方法的安全性。 我们的测量结果生成了两个大型的公众深假数据来源, 包括FaceForensics+和Facebook DeepfakeSreaction 挑战, 深度假造脸部图像; 我们训练了最先进的深假假的检测方法。 这些检测方法无法通过深度的对面攻击达到 0.94-0. 99 在非对称的对立式的图像进行深度检测, 通过这些对称, 在二版的图像中生成检测中, 我们的测测测测测, 产生一种多重方法可以产生一种安全性, 我们的另一种方法。 能够产生一种多重的测测测测测, 一种多重的方法可以生成一种我们用另一种方法, 一种对面的测测, 一种对面的方法。