Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Leaking YouTube creators' private videos

javoriuski.com

Post reply on HN
Print view View original

291–300 of 436 posts

Re: Leaking YouTube creators' private videos

#291

Post by keepamovin »

orbital-decay wrote: post #286
keepamovin wrote: post #258

Earlier quoted context omitted.

Isn’t it trivially fixable by having a monitor LLM? The monitor just reviews each turn pair and asks, “Is this conversation being manipulated via prompt injection?”

Such LLM would be susceptible to injections itself, even if it's not instruction-tuned (or it would be too dumb to work as a reliable guardrail). Chain injections are trivial enough, current black box style agentic systems are easily reverse engineered in practice if you have any understanding. You can mitigate it in a way similar to the security of any human organization, but fundamentally it's a cat and mouse game,…

I understand that sounds possible in theory but honestly cannot conjure an example. Care to?

Even if, doesn't the monitor separation make it immune enough? I feel this is one of those "exponential" benefits things - if one is not enough, add more! A chain of monitors - "Am i being manipulated?" "Am I being manipulated?" and so on. At some point, the monitors win (and maybe approximate consciousness processes), and the prompts lose.

It's interesting how close it is to "social engineering" and security/espionage organizationally. I guess the crucial difference is that incentives can be more rigorously controlled.

Re: Leaking YouTube creators' private videos

#293

Post by keepamovin »

zapkyeskrill wrote: post #272
keepamovin wrote: post #258

Earlier quoted context omitted.

Isn’t it trivially fixable by having a monitor LLM? The monitor just reviews each turn pair and asks, “Is this conversation being manipulated via prompt injection?”

Is it? Or does it just make it multi dimensional? As in, prompt now need to anticipate there being a monitor and instruct that one too, indirectly.

Right - but that sounds too intractable to hold up. See my other comment, I feel a chain of monitors defeats it. But hey! Who knows?

Re: Leaking YouTube creators' private videos

#294

Post by alfiedotwtf »

Mg6yDfjp5U wrote: post #10

I recently left Google having worked on a number of projects with various YouTube teams. I think I can explain why it's being handled this way by YouTube. This is a fairly nuanced/involved issue, so the task of classifying the bug likely made it's way to one of the engineers responsible for the implementation of this feature. That engineer has already launched this project, and filed it away under their GRAD (perform…

Holy shit working at Google sounds depressing AF

Re: Leaking YouTube creators' private videos

#295

Post by fragmede »

blini-kot wrote: post #288
NamTaf wrote: post #149

Earlier quoted context omitted.

[flagged]

yeah, and somebody mounting i.e. some sort of audio/video equipment might make a mistake of putting flammable wire through firewall, while a software engineer in a different field (i.e. embedded or network firewall) might get lawful action in case of a design flaw Licenses and reprimands are not bulletproof as those are often portrayed: take 737MAX for example, or Ford Pinto, or bridges, which fail every day as it se…

The post-mortem on an incident is where it's at. Unfortunately most of those are proprietary and unseen by the rest of the world, but when a load bearing (are humans allowed to user that phrase still?) website like Google or Stripe went down, there's a level of rigor that isn't seen by the public to ask the five why's, or another framework that makes software look like real engineering. Problems are going to happen. Things after going to come up. The question is what you do after that, which determines if it's a serious thing or not.

Re: Leaking YouTube creators' private videos

#296

Post by jdiff »

keepamovin wrote: post #293
zapkyeskrill wrote: post #272

Earlier quoted context omitted.

Is it? Or does it just make it multi dimensional? As in, prompt now need to anticipate there being a monitor and instruct that one too, indirectly.

Right - but that sounds too intractable to hold up. See my other comment, I feel a chain of monitors defeats it. But hey! Who knows?

An n-deep chain of monitors doesn't really have any defense that an (n-1)-deep chain of monitors has. None of them have the capacity to separate data and instructions. All you're doing is (in some ways) giving the model more rolls of the dice to catch what's going on, but the kind of dice and the needed values to roll are in the attacker's hands as much as yours.

Re: Leaking YouTube creators' private videos

#297

Post by Crestwave »

Aachen wrote: post #249

I don't understand, how does this leak a private video title¹ when you need to post a comment on the video you want to leak? Aren't you on the video page at that point? And the creator needs to click the link inside of a comment section or summary thereof. I disagree with Google saying that phishing vectors are irrelevant for security (it's basically the top vector and Google knows that), but it's hard to disagree wi…

The scenario described in the OP does not involve commenting on a private video. It involves commenting on any public video, then the uploader clicks on a suggested prompt in YouTube Studio which supposedly processes the comment and creates a URL with the title of a different video.

Re: Leaking YouTube creators' private videos

#298

Post by sieabahlpark »

Mg6yDfjp5U wrote: post #10

I recently left Google having worked on a number of projects with various YouTube teams. I think I can explain why it's being handled this way by YouTube. This is a fairly nuanced/involved issue, so the task of classifying the bug likely made it's way to one of the engineers responsible for the implementation of this feature. That engineer has already launched this project, and filed it away under their GRAD (perform…

[dead]

Re: Leaking YouTube creators' private videos

#299

Post by sieabahlpark »

NamTaf wrote: post #149
Mg6yDfjp5U wrote: post #10

I recently left Google having worked on a number of projects with various YouTube teams. I think I can explain why it's being handled this way by YouTube. This is a fairly nuanced/involved issue, so the task of classifying the bug likely made it's way to one of the engineers responsible for the implementation of this feature. That engineer has already launched this project, and filed it away under their GRAD (perform…

[flagged]

[dead]

Re: Leaking YouTube creators' private videos

#300

Post by esrauch »

Mg6yDfjp5U wrote: post #72
varispeed wrote: post #62

Earlier quoted context omitted.

> This is a fairly nuanced/involved issue Is it though?

Definitely. The front line support agents handle only the most basic requests. Anything even remotely complicated, such as this, would be internally kicked around until they found someone familiar with the project to give input. Which most likely is someone who worked on the original implementation.

In 2026 things have changed, there's literally whatever tens of thousands of "security" reports that are almost all bogus as a raging crap river.

I think theres very little chance this particular report made it to any engineer who works on product at all, because if they did they would be completely overwhelmed by reports, the filter which has to handle the many thousands of reports based on a playbook almost definitely filtered it out before it made it that far.

Post reply on HN