Project

Detect DeepFakes: How to counteract misinformation created by AI

Creative Commons

Attribution 4.0 International

Matt

Project Contact:
Groups

Participate in the experiment at https://detectfakes.media.mit.edu

Check out our publications in PNAS, a workshop at IJCAI, and pre-print on arXiv. 

Check out a video from the Election Misinformation Symposium: Fighting Misinfo Through Fact-checking and Deepfake Detection

Find our deepfake research discussed in the news: Scientific American, BBC, WSJ, NYT, , and NPR 

How do you spot a DeepFake? How good are DeepFake videos? How well can ordinary people tell the difference between a video manipulated by AI and a normal, non-altered video? Rather than try to explain in words, we built the Detect Fakes website so you can see the answer for yourself. Detect Fakes is a research project designed to answer these questions and identify techniques to counteract AI-generated misinformation. It turns out there are many subtle signs that a video has been algorithmically manipulated. Some subtleties are explained in detail below.

Participate in the experiment at https://detectfakes.media.mit.edu

Check out our publications in PNAS, a workshop at IJCAI, and pre-print on arXiv. 

Check out a video from the Election Misinformation Symposium: Fighting Misinfo Through Fact-checking and Deepfake Detection

Find our deepfake research discussed in the news: Scientific American, BBC, WSJ, NYT, , and NPR 

How do you spot a DeepFake? How good are DeepFake videos? How well can ordinary people tell the difference between a video manipulated by AI and a normal, non-altered video? Rather than try to explain in words, we built the Detect Fakes website so you can see the answer for yourself. Detect Fakes is a research project designed to answer these questions and identify techniques to counteract AI-generated misinformation. It turns out there are many subtle signs that a video has been algorithmically manipulated. Some subtleties are explained in detail below.

Research Topics
#human-computer interaction #artificial intelligence #data #government #human-machine interaction #social media #social science #machine learning #computer science #technology

Creative Commons

Attribution 4.0 International

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. 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). 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 were awarded $1,000,000. 

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. 

We hypothesized 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. As such, we hosted a website called Detect Fakes to display thousands of the curated, high-quality DeepFake and real videos from the DFDC dataset publicly.  The latest version of the website shows 32 videos that were produced as part of the Presidential Deepfakes Dataset.

The Detect Fakes experiment offers the opportunity to learn more about DeepFakes and see how well you can discern real from fake. When it comes to AI-manipulated media, there's no single tell-tale sign of how to spot a fake. Nonetheless, there are several DeepFake artifacts that you can be on the look out for. 

  1. Pay attention to the face. High-end DeepFake manipulations are almost always facial transformations. 
  2. Pay attention to the cheeks and forehead. Does the skin appear too smooth or too wrinkly? Is the agedness of the skin similar to the agedness of the hair and eyes? DeepFakes may be incongruent on some dimensions.
  3. Pay attention to the eyes and eyebrows. Do shadows appear in places that you would expect? DeepFakes may fail to fully represent the natural physics of a scene. 
  4. Pay attention to the glasses. Is there any glare? Is there too much glare? Does the angle of the glare change when the person moves? Once again, DeepFakes may fail to fully represent the natural physics of lighting.
  5. Pay attention to the facial hair or lack thereof. Does this facial hair look real? DeepFakes might add or remove a mustache, sideburns, or beard. But, DeepFakes may fail to make facial hair transformations fully natural.
  6. Pay attention to facial moles.  Does the mole look real? 
  7. Pay attention to blinking. Does the person blink enough or too much? 
  8. Pay attention to the lip movements. Some deepfakes are based on lip syncing. Do the lip movements look natural?

These eight questions are intended to help guide people looking through DeepFakes. High-quality DeepFakes are not easy to discern, but with practice, people can build intuition for identifying what is fake and what is real. You can practice trying to detect DeepFakes at Detect Fakes.