One of the first real-world applications for deepfakes was, in fact, to create synthetic pornography. While the ability to automatically swap faces to create credible and realistic looking synthetic video has some interesting benign applications (such as in cinema and gaming), this is obviously a dangerous technology with some troubling applications. Many experts believe that, in the future, deepfakes will become far more sophisticated as technology further develops and might introduce more serious threats to the public, relating to election interference, political tension, and additional criminal activity. Some of these apps are used for pure entertainment purposes - which is why deepfake creation isn't outlawed - while others are far more likely to be used maliciously.
ZAO DEEPFAKE APP WASHINGTON POST SOFTWARE
Several apps and softwares make generating deepfakes easy even for beginners, such as the Chinese app Zao, DeepFace Lab, FaceApp (which is a photo editing app with built-in AI techniques), Face Swap, and the since removed DeepNude, a particularly dangerous app that generated fake nude images of women.Ī large amount of deepfake softwares can be found on GitHub, a software development open source community.
ZAO DEEPFAKE APP WASHINGTON POST HOW TO
GANs are also used as a popular method for creation of deepfakes, relying on the study of large amounts of data to "learn" how to develop new examples that mimic the real thing, with painfully accurate results. The autoencoder is a deep learning AI program tasked with studying the video clips to understand what the person looks like from a variety of angles and environmental conditions, and then mapping that person onto the individual in the target video by finding common features.Īnother type of machine learning is added to the mix, known as Generative Adversarial Networks (GANs), which detects and improves any flaws in the deepfake within multiple rounds, making it harder for deepfake detectors to decode them. The videos can be completely unrelated the target might be a clip from a Hollywood movie, for example, and the videos of the person you want to insert in the film might be random clips downloaded from YouTube. You first need a target video to use as the basis of the deepfake and then a collection of video clips of the person you want to insert in the target. There are several methods for creating deepfakes, but the most common relies on the use of deep neural networks involving autoencoders that employ a face-swapping technique. Deep learning algorithms, which teach themselves how to solve problems when given large sets of data, are used to swap faces in video and digital content to make realistic-looking fake media. The term "deepfake" comes from the underlying technology "deep learning," which is a form of AI.