#DEEP FAKES HOW TO#
When it comes to AI-manipulated media, there's no single tell-tale sign of how to spot a fake. The Detect Fakes experiment offers the opportunity to learn more about DeepFakes and see how well you can discern real from fake. As such, we hosted a website called Detect Fakes to display thousands of these curated, high-quality DeepFake and real videos publicly. We hypothesize that the exposure of how DeepFakes look and the experience of detecting subtle computational manipulations will increase people's ability to discern a wide-range of video manipulations in the future.
Many of the manipulations are very subtle. All manipulations are facial or audio manipulations. These videos are particularly useful for highlighting the nuances of DeepFakes because they showcase a diversity of people, lighting conditions, and algorithmic manipulation techniques. These videos are not just hard for a machine learning model to discern, but they are hard for many people to discern between fake and real. In other words, we chose the videos that the model predicted with high certainty that they were real videos when in fact these videos were manipulated by AI. Based on our machine learning model's performance, we filtered the collection of videos to the 3,000 on which the model was most confidently wrong. These videos show actors who consented to the DFDC making manipulations of their likenesses.
#DEEP FAKES SERIES#
Rather than fine-tune the best machine learning model for this Kaggle competition, we are curious about strategies and techniques for building public awareness of DeepFake technology and helping ordinary people think critically about the media that they consume.įrom 100,000 DeepFake videos and 19,154 real videos hosted on the public Kaggle competition, we trained a series of neural networks to detect DeepFakes. The goal of the challenge is to spur researchers around the world to build innovative new technologies that can help detect deepfakes and manipulated media." The winners of the Kaggle Competition will be awarded $1,000,000 in total. The description on the Kaggle Website explains, "AWS, Facebook, Microsoft, the Partnership on AI’s Media Integrity Steering Committee, and academics have come together to build the Deepfake Detection Challenge (DFDC). We already know DeepFakes can be quite believable, but just how believable are they? Kaggle's Deepfake Detection Challenge (DFDC) recently sought an algorithmic answer to this question of detecting fakes.
0 kommentar(er)
