Live data from Hacker News

AI Art Generators Can Be Fooled into Making NSFW Images

spectrum.ieee.org

151–160 of 193 posts

Re: AI Art Generators Can Be Fooled into Making NSFW Images

#151

If you want porn, there are Stable Diffusion models out there that will generate it. There's one model that seems to generate nudes by default; if you don't ask for clothes, you don't get them. Whatever. This isn't important. What is important is that we can't prevent LLMs from doing things they're not supposed to. Which means connecting their output to anything important is a very bad idea for now.

> connecting their output to anything important is a very bad idea for now. This may be true for images, but at least for text, treating an LLM as an untrusted person in your threat models will at least allow you to apply defense in depth to the downstream systems consuming from the LLMs Tldr: engineer other systems to treat LLMs as a potentially bad actor by default.

Unfortunately, when the CIO screams about deadlines and people want to keep their jobs, most of that goes out the window.

Re: AI Art Generators Can Be Fooled into Making NSFW Images

#152

And people can be fooled into making dirty jokes (that's what she said). A pointless endeavour to solve a problem that shouldn't be solved.

Imagine the benefits a safe image generator would have on children, them learning to explain what they want to see, how it should be changed. A house with a tree and a dog and a lake nearby, instead of playing candy crush. Why shouldn't it be solved? We clearly differ.

At least for the time being, I’ll put my trust in Crayola for that, rather than OpenAI. Alternatively, if we really must have children interacting with image generation, it seems like a great opportunity for parents to have some bonding time with their kids.

Re: AI Art Generators Can Be Fooled into Making NSFW Images

#153
post #98
post #20

Earlier quoted context omitted.

The latter would be preferred by most, and is most aligned with individualism, but sadly that is not where we are as a society. There are an entire class of people who believe they know what is best for you, about nearly every subject matter, and wish to limit all aspects of technology, life, politics, etc, to suit their superior beliefs.

Alternatively, would you rather a world with 80% functionality safely, or a world with 100% functionality with people you don’t trust doing malicious things? One is clearly the least worst

We must have different definitions of the word “clearly”. I’ll take that full model in a heartbeat, but I suspect many others would disagree.

Re: AI Art Generators Can Be Fooled into Making NSFW Images

#154
post #140

Are NSFW images are really a problem? The problem are NSFLE (not safe for law enforcement) pictures and the question is, should they be really illegal if artificially created.

This is a discussion that will turn many heads red before a proper solution is found

Assuming a “proper” solution exists. There are many world views that conflict with each other, and quite a few of those have the belief that they must “save” the people who have not reached their own “enlightened” viewpoint.

Re: AI Art Generators Can Be Fooled into Making NSFW Images

#155

It is impressive how much effort the human race is spending trying to prevent algorithms from generating pictures of naked people.

why do people have to always try to convince me how unfazed they are by nudity? if you're unfazed by it, please link me to your nudes. if not, you're fazed. there's absolutely nothing wrong with finding certain states of undress offensive. would you vote for or against buttholes on display on bus kiosks? i'm against. on the other hand, making an arbitrary line, and seeing if an AI can detect/enforce it is an interest…

An interesting take given your choice of username. CS challenges aside, who gets to draw the line?

Re: AI Art Generators Can Be Fooled into Making NSFW Images

#156
post #52

Earlier quoted context omitted.

Let's focus on trying to raise a mentally healthier generation and take mental illness more seriously, rather than banning / getting rid of all the things that might cause someone (let alone a teenager) to commit suicide (an infinite set).

Boiling the ocean type solutions are the same as doing nothing. A better solution would be to make creating such things very illegal and bring down the same wrath we do for CSAM. There is no amount of "mental health" that can protect you against targeted bullying of that magnitude. I really wish we had a universe simulator so you could see how miserably you would fail to survive an environment like that.

Perhaps we need to spend some time working on the mental health of those who bully others. At the moment, we seem to, mostly, turn a blind eye to it, or use “zero tolerance” policies (which, IMO, are even more harmful to the victims than the bullying) to act like we’ve solved the problem.

I don’t pretend to have the answer, but admitting that there’s a problem in the first place is a good step forward.

Re: AI Art Generators Can Be Fooled into Making NSFW Images

#157

And people can be fooled into making dirty jokes (that's what she said). A pointless endeavour to solve a problem that shouldn't be solved.

Imagine the benefits a safe image generator would have on children, them learning to explain what they want to see, how it should be changed. A house with a tree and a dog and a lake nearby, instead of playing candy crush. Why shouldn't it be solved? We clearly differ.

If the children manage to induce LLM into generating NSFW content, they are probably capable of inducing their set of coloring pen into drawing dick shapes.

Re: AI Art Generators Can Be Fooled into Making NSFW Images

#158
post #128

It seems like such a pointless exercise .... it's so unsurprising that if you try really hard to break something by violating it's design constraints that ... it breaks. Like, if I said I was going to find out if you can smash a car by driving it directly into a tree and then wrote an article about it. The really useful point of building the constraints in is to ensure we don't get offensive content by accident. Espe…

> It seems like such a pointless exercise…

“Hacking [thing] is pointless” is a surprising take to read here.

Re: AI Art Generators Can Be Fooled into Making NSFW Images

#159

It is impressive how much effort the human race is spending trying to prevent algorithms from generating pictures of naked people.

why do people have to always try to convince me how unfazed they are by nudity? if you're unfazed by it, please link me to your nudes. if not, you're fazed. there's absolutely nothing wrong with finding certain states of undress offensive. would you vote for or against buttholes on display on bus kiosks? i'm against. on the other hand, making an arbitrary line, and seeing if an AI can detect/enforce it is an interest…

> why do people have to always try to convince me how unfazed they are by nudity? if you're unfazed by it, please link me to your nudes. if not, you're fazed.

This ignores people who are comfortable with nudity, but are not comfortable with the puritans (i.e. most humans) harassing them for being in their natural state.

> there's absolutely nothing wrong with finding certain states of undress offensive. would you vote for or against buttholes on display on bus kiosks? i'm against.

Great strawman. Nudity is normal. Finding other people's states of undress offensive, and wanting to criminalise them, when they do not harm you at all, is a bigoted view.

Re: AI Art Generators Can Be Fooled into Making NSFW Images

#160

Together with fancy silicon chips, AI models and everything else that's being exported from the US , the world has to endure this puritanistic views export too.

some parts of east asia and middle east are much, much, Much worse. Not just "puritanistic" but down to "these kinds of people do not exist".
Post reply on HN