You don’t need a whole lot of imagination to realize how it could be used to produce revenge porn that will be all the more devastating to the target’s life because of how realistic some of the nude photos look. In other words, it had all the ingredients necessary to turn an unsuspecting woman’s existence into a living hell. The short-lived app was free, easy to use, and fast - the digital disrobing only took 30 seconds. 8uJKBQTZ0o- deepnudeapp June 27, 2019ĭamn straight. In an excellent example of how public scrutiny can bring unethical AI-powered tech to a halt, the developer then said he realized that “the probability that people will misuse it is too high.” So it was really great news when, just days after he released the app, the programmer behind it decided to shut it down on Thursday.Īfter Motherboard first reported on the “horrifying” new app, other news outlets followed suit with critical coverage. Even if you’ve never posed naked for a photo in your life, anyone who downloads DeepNude can make it look as if you did. This app is the latest evolution of AI-powered deepfake technology, which makes it disturbingly easy to doctor images to make it look like someone said or did something they never actually said or did. The result is pretty realistic - and blatantly unethical. If you feed it a picture of a clothed woman, it removes her clothes so that she appears naked. The nature and meaning of these transformations are not very important, and have been discovered after numerous trial and error attempts.An anonymous programmer created a new app called DeepNude that uses AI to create nonconsensual porn. To optimize the result, simple computer vision transformations are performed before each GAN phase, using OpenCV. Although it is possible to use some automations, the creation of these datasets still require great and repetitive manual effort. Working on stylized and abstract graphic fields the construction of these datasets becomes a mere problem of hours working on photoshop to mask photos and apply geometric elements. Web scrapers can download thousands of images from the web, dressed and nude, and through photoshop you can apply the appropriate masks and details to build the dataset that solve a particular sub problem. This approach makes the construction of the sub-datasets accessible and feasible. Generation of a abstract representation of anatomical attributes.Generation of a mask that selects clothes.Instead of relying on a single network, we divided the problem into 3 simpler sub-problems: We overcome the problem using a divide-et-impera approach. A database in which a person appears both naked and dressed, in the same position, is extremely difficult to achieve, if not impossible. Paired datasets get better results and are the only choice if you want to get photorealistic results, but there are cases in which these datasets do not exist and they are impossible to create. If you are interested in the details of the network you can study this amazing project provided by NVIDIA.Ī GAN network can be trained using both paired and unpaired dataset. The algorithm uses a slightly modified version of the pix2pixHD GAN architecture. The input image should be 512px * 512px in size (parameters are provided to auto resize/scale your input).ĭreamPower uses an interesting method to solve a typical AI problem, so it could be useful for researchers and developers working in other fields such as fashion, cinema and visual effects. This will print out help on the parameters the algorithm accepts.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |