Facebook's 'Deepfake Detection Challenge' yields promising early results

Devin Coldewey

The digitally face-swapped videos known as deepfakes aren't going anywhere, but if platforms want to be able to keep an eye on them, they need to find them first. Doing so was the object of Facebook's "Deepfake Detection Challenge," launched last year. After months of competition the winners have emerged, and they're... better than guessing. It's a start!

Since their emergence in the last year or two, deepfakes have advanced from niche toy created for AI conferences to easily downloaded software that anyone can use to create convincing fake video of public figures.

"I've downloaded deepfake generators that you just double click and they run on a Windows box — there's nothing like that for detection," said Facebook CTO Mike Schroepfer in a call with press.

This is likely to be the first election year where malicious actors attempt to influence the political conversation using fake videos of candidates generated in this fashion. Given Facebook's precarious position in public opinion, it's very much in their interest to get out in front of this.

Facebook is making its own deepfakes and offering prizes for detecting them

The competition started last year with the debut of a brand new database of deepfake footage. Until then there was little for researchers to play with — a handful of medium-size sets of manipulated video, but nothing like the huge sets of data used to evaluate and improve things like computer vision algorithms.

Facebook footed the bill to have 3,500 actors record thousands of videos, each of which was present as an original and a deepfake. A bunch of other "distractor" modifications were also made, to force any algorithm hoping to spot fakes to pay attention to the important part: the face, obviously.

Researchers from all over participated, submitting thousands of models that attempt to decide whether a video is a deepfake or not. Here are six videos, three of which are deepfakes. Can you tell which is which? (The answers are at the bottom of the post.)

Image Credits: Facebook

At first, these algorithms were no better than chance. But after many iterations and some clever tuning, they managed to reach more than 80% accuracy in identifying fakes. Unfortunately, when deployed on a reserved set of videos that the researchers had not been provided, the highest accuracy was about 65%.

It's better than flipping a coin, but not by much. Fortunately, that was pretty much expected, and the results are actually very promising. In artificial intelligence research, the hardest step is going from nothing to something — after that it's a matter of getting better and better. But finding out if the problem can even be solved by AI is a big step. And the competition seems to indicate that it can.

Examples of a source video and multiple distractor versions. Image Credits: Facebook

An important note is that the data set created by Facebook was deliberately made to be more representative and inclusive than others out there, not just larger. After all, AI is only as good as the data that goes into it, and bias found in AI can often be traced back to bias in the data set.

"If your training set doesn't have the appropriate variance in the ways that real people look, then your model will not have a representative understanding of that. I think we went through pains to make sure this data set was fairly representative," Schroepfer said.

I asked whether any groups or types of faces or situations were less likely to be identified as fake or real, but Schroepfer wasn't sure. In response to my questions about representation in the data set, a statement from the team read:

In creating the DFDC dataset, we considered many factors and it was important that we had representation across several dimensions including self-identified age, gender, and ethnicity. Detection technology needs to work for everyone so it was important that our data was representative of the challenge.

The winning models will be made open source in an effort to spur the rest of the industry into action, but Facebook is working on its own deepfake detection product that Schropfer said would not be shared. The adversarial nature of the problem — the bad guys learn from what the good guys do and adjust their approach, basically — means that telling everyone exactly what's being done to prevent deepfakes may be counterproductive.

(Answers to deepfake detection image: 1, 4, and 6 are real; 2, 3, and 5 are deepfakes.)

More From

  • Mighty Health created a wellness app with older adults top of mind

    Virtual classes might make it easier to work out anywhere, anytime, but not for anyone. Mainstream fitness tech often targets the young and fit, in advertisements and cardio-heavy exercises. This gap between mainstream fitness and elders is where Mighty Health, a Y Combinator graduate, comes in. Mighty Health has created a nutrition and fitness wellness app that is tailored to older adults who might have achy hips or joint problems.

  • Former Tinder VP Jeff Morris Jr. opens up Product Club, an accelerator meant to stay small and focused

    Startup accelerators tend to grow the size of each new class over time, as more of their portfolio companies find exits, their network of mentors expands and they find new ways to scale things up. VC and former Tinder VP Jeff Morris Jr. is taking a different approach with his new accelerator, Product Club: start small and stay small. The first batch of Product Club companies will be made up of just three companies.

  • SaaS and cloud stocks finally give back ground

    After a heated run, SaaS and cloud stocks dipped sharply during regular trading on Monday. To hear bulls -- both private and public -- tell the story, COVID-19 and its ensuing workplace disruptions have provided software companies with a huge boon.

  • A pledge to unite international students and tech

    The last three-and-a-half years have been hell for immigrants and hell for immigration lawyers. Probably a lot of caring government immigration adjudicators have felt it, too. Many immigrants live in fear that the cost of opening their mouths would be retaliation and deportation.