Hacker News Reader

Comment by mschuster91 | Hacker News Reader

Because that is a trivial task as the question "is there licensed music in the track" is binary and really easy to do given a large enough number of fingerprints.

Detecting if there is a child in the video is more difficult, but do-able with current ML models. Now, however, determining why there is a child in the video - if it is a family "fail" video or pedo material, for example - via AI is about as impossible as trying to distinguish between satire, hate speech or propaganda via AI. It's not possible at all, as AI will for the near future totally lack context.

This distinction will require humans, and this is something not viable at all for fb, youtube, twitter & co, as it is a huge cost... the saving of which is offloaded to society though in form of e.g. undermined democracies or psychological trauma in sexual violence survivors.

View on HN

They already have an AI to detect these videos: the recommendation engine mentioned in the article. These videos aren't difficult to find.

The recommendation engine doesn't know what the content is or in what way it is similar, it just knows that people who view this video often view this other video. On the bright side the recommendation engine grouping all these videos means that once YouTube identifies one video as inappropriate they can easily use the recommendations to find and delete all the other videos that are also being viewed by the same pedos.

> On the bright side the recommendation engine grouping all these videos means that once YouTube identifies one video as inappropriate they can easily use the recommendations to find and delete all the other videos that are also being viewed by the same pedos.

That is exactly the point, they have this ability and are not using it. Not even to disable comments.

Some of the videos were up for months, and youtube did nothing to remove them after being asked.

The "recommendation engine" is a stupid "people searching for x clicked on y" thing. Not intelligent at all.

And banning keywords won't help, that's just whack-a-mole'ing.

> Now, however, determining why there is a child in the video

It doesn't matter why the child is in the video. The pedophile only cares that there is a child. Videos uploaded with children in them will be exploited, regardless of whether they are legitimate.

Banning the public from uploading videos featuring children, or worse, deleting those already there, will be extremely unpopular. And I'm not convinced it's necessary.

I honestly don't think you can do anything about pedophiles watching otherwise innocent videos of children.

The article claims that there is nudity (via timestamp comments). Separate models could be used to score the video, where a child plus any other potentially sexual content (genitalia, nipples) withholds the video. A withheld video can be appealed (for scenarios such as "breastfeeding tips" or what-have-you), much like copyright strikes, which have an existing process.

Obviously the model might have problems discerning between a 17 and 18 year old, but it would catch the most egregious content.

How about disabling comments, proactively deleting illegal content and not helping people find more non-illegal but potentially exploitative content?

I feel like you have missed the point. YouTube is actively helping people find this content and making money off of it.

In this case we will have to ban children movies (Harry Potter?) and TV channels, which sounds too harsh.

As long as child is not performing some sexually suggestive stuff on youtube video ("popsicle challenge", wtf) it is OK, probably.

So we should just ban all videos of children then?

This is not true. ML can detect kids in videos, and if there was any financial incentive to doing so, Youtube could follow their recommendation graph to know exactly what type of content to ban or restrict commenting on.

The reason why they find licensed music in videos is because they have a financial (profit) motive for doing so. Find a licensed track, and get a few fractions of a penny every time someone watches that video. There is no financial incentive to blocking CP, so they don't bother. This is a real shame.

> ML can detect kids in videos

It can't detect context, however.

>The reason why they find licensed music in videos is because

It's technically easier to do so. ML is still new, and it still makes mistakes, this is why people complain about content ID because it takes down videos that are "fair use".

Explain to me, Mr Expert, how a ML algorithm can understand the nuance of the law, interpret it flawlessly like a human would (say, in a court of law).

Unless you're saying these cases no longer require humans, courts and judges, and ML is at a point where it's _flawless_ and accurate 100% of the time.

It's a shame you're so technically weak minded, I thought the Hackernews community would be educated in this regard.

Please go read about how ML works before making such comments in the future, they make you look really stupid.

>> ML can detect kids in videos > It can't detect context, however.

You don't actually need to, at least initially. You only need to detect kids, and when you have some threshold of reports on comments on a video where the computer vision algorithm detected kids in the frame that rise to the level a human should take a look, the human can flag the video as containing elements of CP, which would kick in the following: - Deeper ML analysis of the dependency graph of commentors, related videos. - Blacklisting or law enforcement notification for commentors that are violating the law. - Training data that can be used to train more advanced algorithms.

Because there is no profit motive to do so, like there is with music licensing, they won't do it.

> It's technically easier to do so.

I'm not talking about determining context with ML. That is a hard problem, of course. But identifying "child human" with a computer vision algorithm is very simple, then relying on human moderators to initiate the dependency graph traversal.

> Please go read about how ML works before making such comments in the future, they make you look really stupid.

No need for the ad hominem. I'm not an ML expert, but I understand enough of the basics to know what is possible.

> ML can detect kids in videos

Even dental scans and x-rays can't give you a reliable chronological age for somebody [0].

In that context, I consider it extremely doubtful that some ML algorithm solved this whole problem by just using pictures/visual recording, that sounds a bit too much like magic/wishful thinking.

[0] https://www.newscientist.com/article/mg21428644-300-with-no-...

The quick & dirty solution here would be to disable comments if children are detected

The problem with that is YouTube's awful history of and approach to false positives.

People would be a lot more willing to accept blanket and risky experiments to solve these problems if there was a viable and reliable reconciliatory/redemptive path for when those systems get it wrong.

For better or worse, YouTube hasn't focused on scaling that part of their system, so there will be apprehension and scepticism with any approach they take.

They could also use their own recommendation engine to flag videos for manual review.

Reply on news.ycombinator.com