# DeepFake Detector AIs Are Good Too!

## Метаданные

- **Канал:** Two Minute Papers
- **YouTube:** https://www.youtube.com/watch?v=RoGHVI-w9bE
- **Дата:** 12.10.2019
- **Длительность:** 5:03
- **Просмотры:** 1,238,046
- **Источник:** https://ekstraktznaniy.ru/video/14239

## Описание

❤️ Pick up cool perks on our Patreon page: https://www.patreon.com/TwoMinutePapers

📝 The paper "FaceForensics++: Learning to Detect Manipulated Facial Images" is available here:
http://www.niessnerlab.org/projects/roessler2019faceforensicspp.html

❤️ Watch these videos in early access on our Patreon page or join us here on YouTube: 
- https://www.patreon.com/TwoMinutePapers
- https://www.youtube.com/channel/UCbfYPyITQ-7l4upoX8nvctg/join

 🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible:
Alex Haro, Andrew Melnychuk, Angelos Evripiotis, Anthony Vdovitchenko, Brian Gilman, Bryan Learn, Christian Ahlin, Claudio Fernandes, Daniel Hasegan, Dennis Abts, Eric Haddad, Eric Martel, Evan Breznyik, Geronimo Moralez, James Watt, Javier Bustamante, John De Witt, Kaiesh Vohra, Kasia Hayden, Kjartan Olason, Levente Szabo, Lorin Atzberger, Lukas Biewald, Marcin Dukaczewski, Marten Rauschenberg, Matthias Jost,, Maurits van Mastrigt, Michael Albrecht, Michael

## Транскрипт

### <Untitled Chapter 1> []

Dear Fellow Scholars, this is Two Minute Papers with Károly Zsolnai-Fehér. We talked about a technique by the name Face2Face back in 2016, approximately 300 videos ago. It was able to take a video of us and transfer our gestures to a target subject. With techniques like this, it’s now easier and cheaper than ever to create these deepfake

### Real-time Facial Reenactment [0:17]

videos of a target subject provided that we have enough training data, which is almost certainly the case for people who are the most high-value targets for these kinds of operations. Look here. Some of these videos are real, and some are fake. What do you think, which is which? Well, here are the results - this one contains artifacts and is hence easy to spot, but the rest…it’s tough. And it’s getting tougher by the day. How many did you get right? Make sure to leave a comment below. However, don’t despair, it’s not all doom and gloom. Approximately a year ago, in came FaceForensics, a paper that contains a large dataset of original

### FaceForensics: Identifying Facial Forgeries [0:59]

and manipulated video pairs. As this offered a ton of training data for real and forged videos, it became possible

### FaceForensics Task 2: Segmentation [1:08]

to train a deepfake detector. You can see it here in action as these green to red colors showcase regions that the AI correctly thinks were tampered with. However, this followup paper by the name FaceForensics++ contains not only an improved dataset, but provides many more valuable insights to help us detect these DeepFake videos, and

### FaceForensics++ [1:33]

even more. Let’s dive in. Key insight number one. As you’ve seen a minute ago, many of these DeepFake AIs introduce imperfections, or in

### Video Gathering [1:43]

other words, artifacts to the video. However, most videos that we watch on the internet are compressed, and the compression procedure…you have guessed right, also introduces artifacts to the video.

### Manipulation [1:53]

From this, it follows that hiding these DeepFake artifacts behind compressed videos sounds

### FaceSwap [2:02]

like a good strategy to fool humans and detector neural networks likewise, and not only that, but the paper also shows us by how much exactly. Here you see a table where each row shows the detection accuracy of previous techniques and a new proposed one, and the most interesting part is how this accuracy drops when we go from HQ to LQ, or in other words, from a high-quality video to a lower-quality one with more compression artifacts. Overall, we can get an 80-95% success rate, which is absolutely amazing. But, of course, you ask, amazing compared to what? Onwards to insight number two. This chart shows how humans fared in DeepFake detection, as you can see, not too well. Don’t forget, the 50% line means that the human guesses were as good as a coinflip, which means that they were not doing well at all. Face2face hovers around this ratio, and if you look at NeuralTextures, you see that this is a technique that is extremely effective at fooling humans. And wait…what’s that? For all the other techniques, we see that the grey bars are shorter, meaning that it’s more difficult to find out if a video is a DeepFake because its own artifacts are hidden behind the compression artifacts. But the opposite is the case for NeuralTextures, perhaps because its small footprint on the videos. Note that a state of the art detector AI, for instance, the one proposed in this paper does way better than these 204 human participants.

### Detection [3:39]

This work does not only introduce a dataset, these cool insights, but also introduces a detector neural network. Now, hold on to your papers because this detection pipeline is not only so powerful that it practically eats compressed DeepFakes for breakfast, but it even tells us with remarkable accuracy

### Method Classification [3:57]

which method was used to tamper with the input footage. Bravo! Now, it is of utmost importance that we let the people know about the existence of these techniques, this is what I am trying to accomplish with this video. But that’s not enough, so I also went to this year’s biggest NATO conference and made sure that political and military decision makers are also informed about this topic. Last year, I went to the European Political Strategy Center with a similar goal. I was so nervous before both of these talks and spent a long time rehearsing them, which delayed a few videos here on the channel. However, because of your support on Patreon, I am in a fortunate situation where I can focus on doing what is right and what is the best is for all of us, and not worry about

### Pick up cool perks on Patreon! [4:47]

the financials all the time. I am really grateful for that, it really is a true privilege. Thank you. If you wish to support us, make sure to click the Patreon link in the video description. Thanks for watching and for your generous support, and I'll see you next time!