Still you can’t tell what kind of object it is supposed to be. 1: Generation of textures, not objectsīoth pictures look very real to start with, but if you look closer, several details look strange in the second picture: (All following examples are from So, which person in the following examples is real? Example no. Keeping this in mind, we will now try to reveal the fake pictures. As the GANs that generate the images are built on top of CNNs, they inherit their weaknesses. However, CNNs have no “concept” of a complete or final image. CNNs merely “learn” vast amounts of fragments (textures) by heart and develop an intuition about how these snippets can be put together and interpolated (mixed). We don’t need to go into detail here, it suffices to know that these networks do not develop any idea of the three-dimensional world. These are currently the state-of-the-art when it comes to processing or generating images. We are referring to so-called CNNs (Convolutional Neural Networks or ConvNets). In this context it is good to know how a specific type of neural network works. It tries to imitate these individual elements, such as facial features, as authentically as possible. The AI has only “learned” to recognize things it was trained for, being shown thousands, better even millions, of examples. It does not even “know” what a face, a human being, top, bottom, left, right, glasses or an ear is. Meaning, it has no world knowledge, common sense, self-consciousness, etc. To get a clue how to “detect” an AI, let’s remember briefly what the weaknesses of current AI are. The most important rule for the recognition of generated images (and also text, speech or video) is that we take a moment, take a deep breath and look closely (which is generally recommended for media consumption). Fragments without context – AI and its flaws Using some examples, we therefore want to explain how computer-generated images can be recognized.Īt the same time, we can additionally learn more about how the current generation of Neural Networks works.īut first things first: The technology in this area is advancing rapidly – it is quite possible that in the near future some of the mentioned handicaps of GANs will be overcome (or that GANs will be replaced by a completely different, new technology). In the “postfactual age”, brimming with digital misinformation, conspiracy theories and fake news on Facebook or social media, a competence in recognizing these deepfakes becomes more important than ever. Yet for an amateur it might become increasingly difficult. If you are familiar with the technology behind it, it is (still) rather easy to distinguish fake from real photos after a little bit of practice. In a quiz you can check your skill in telling fake from real photos, without resorting to tricks like the Reverse Image Search on Google. demonstrates how good these results are.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |