Deepak (Deepak) is, in fact, a photo, video or audio material that is not real, fake, that is, fake. Deepfake (combination of two words - deep learning "deep learning" and fake "fake") uses artificial intelligence (AI) for deep learning to create the likeness of one person with another in videos and other digital media materials. It is created by algorithms based on real voice, sound, video or photo samples that are stitched together. The algorithm takes selected information from many different places and then combines it into one material. As a result, something new (false) is created, which is based on a combination of different real data. But that's not all.
Deepfake can also "paint" a photo from scratch, for example by creating the faces of characters that never existed. What is the purpose of such actions? Among other things, Deepfake is used to spread incorrect information on the Internet (for example, about political figures or events), theft (for example, forging voice Switzerland WhatsApp Number List acommands) and creating pornography (movies with celebrities - deepfake porn). It can also be used for educational and entertainment purposes. Deepfake - How does it work? In general, there are two ways to create deepfake material. The first method uses two algorithms. First, the first (encoder) looks for common features of two images (those to be combined into one.
Then the second (decoder) can transfer them to the newly created image. For example, if we want to create a video in which an actor would move like us, the encoder takes the movement from the video where we are dancing, and the decoder will already replace our face with the actor's face and make him reproduce our movements. The key here is the selected actions that are copied to the new image (for example, movements, gestures, facial expressions). The second way is through generative adversarial networks (GANs), where two algorithms work together.