| ||||
 |
 |
Question:
I’ve heard the term “deepfake videos” in the news lately. What are they? How and why are they made?
Answer: A deepfake is a technique for human image synthesis based on artificial intelligence. By using this technique, creators can show real people in videos doing and saying things they never did. Deepfake videos are designed to intentionally mislead people. While they can be used for entertainment and satire on TV and social media (where it’s usually identified as such), deepfakes are more often produced by people with an ax to grind, an agenda to promote, or an urge to troll. They’re created by using two competing AI systems — one is called the generator and the other is called the discriminator. Basically, the generator creates a fake video clip and then asks the discriminator to determine whether the clip is real or fake. Each time the discriminator accurately identifies a video clip as being fake, it gives the generator a clue about what not to do when creating the next clip. Spotting a deepfake video can be challenging, but watch for the following characteristics:
|
|
|
