How journalists use youtube-dl

Re:How journalists use youtube-dl by motohagiography on Monday October 26, 2020 @05:14PM (#24901502)

I used ffmpeg and audacity with youtube-dl to download and do file and spectrograph analysis on a faked political video. That analysis showing how the audio was spliced together may have killed the story before it got legs.

In an era of fakes and deepfakes, we need tools like youtube-dl more than ever.

[ Parent | on HN ]

Re:How journalists use youtube-dl by kortex on Monday October 26, 2020 @10:36PM (#24904013)

> In an era of fakes and deepfakes, we need tools like youtube-dl more than ever.

I've been working on deepfake detection for the past two years. I use pytube3 and youtube-dl to scrape hours and hours of footage, not just youtube, but cspan, news sites, anything I can get my hands on. I have ~100 hours pulled so far, at multiple encoding rates.

Facebook recently changed their API and now the best I can scrape easily is 240p. That's insufficient to detect the artifacts the models need to train on. I can only pull 1/3rd of cspan videos I can watch through the viewer because again, api changes. It's a constant cat and mouse.

I'm not exaggerating when I say that if I don't have those wonderful folks out there keeping these tools and test suites up-to-date, this project is massively disadvantaged.

I don't have any public release assets at the moment, but you can read about Siwei Lyu and Hany Farid, who are leading the charge in deepfake detection.

http://www.cs.albany.edu/~lsw/

https://futurism.com/expert-online-disinfo-covid-black-lives...

[ Parent | on HN ]

Re:How journalists use youtube-dl by brokenmachine on Monday October 26, 2020 @07:55PM (#24902998)

Did you post an article about it? I'd be interested to read it.

[ Parent | on HN ]

Re:How journalists use youtube-dl by lostgame on Monday October 26, 2020 @08:03PM (#24903075)

This is probably one of the coolest and most underrated comments in this topic!

Could you tell us more about this process?

[ Parent | on HN ]

Re:How journalists use youtube-dl by motohagiography on Monday October 26, 2020 @09:28PM (#24903626)

Thanks, it's way less cool when I write spectrogram instead of spectrograph. My mistake on that part.

If you use those tools, it's really straight forward process of using the tools. I didn't know about Audacity until I had spent most of my time figuring out ffmpeg/ffplay. It was an amateur effort, but I've done a lot of security analysis.

[ Parent | on HN ]

Re:How journalists use youtube-dl by AnonsLadder on Monday October 26, 2020 @05:59PM (#24901999)

That's freaking awesome

[ Parent | on HN ]