Submitted 11 months ago by L4s@lemmy.world [bot] to technology@lemmy.world
Data poisoning: how artists are sabotaging AI to take revenge on image generators::As AI developers indiscriminately suck up online content to train their models, artists are seeking ways to fight back.
Takes image, applies antialiasing and resize
Oh, look at that, defeated by the completely normal process of preparing the image for training
Unfortunately for them there’s a lot of jobs dedicated to cleaning data so I’m not sure if this would even be effective. Plus there’s an overwhelming amount of data that isn’t “poisoned” so it would just get drowned out if never caught
Imagine if writers did the same things by writing gibberish.
At some point, it becomes pretty easy to devalue that content and create other systems to filter it.
if writers did the same things by writing gibberish.
Aka, “X”
I mean isn’t that eventually going to happen? Isn’t ai going to eventually learn and get trained from ai datasets and small issues will start to propagate exponentially?
I just assume we have a clean dataset preai and messy gross dataset post ai… If it keeps learning from the latter dataset it will just get worse and worse, no?
Not really. It’s like with humans. Without the occasional reality checks it gets weird, but what people chose to upload is a reality check.
The pre-AI web was far from pristine, no matter how you define that. AI may improve matters by increasing the average quality.
nightshade and glaze never worked. its scam lol
Shhhhh.
Let them keep doing the modern equivalent of “I do not consent for my MySpace profile to be used for anything” disclaimers.
It keeps them busy on meaningless crap that isn’t actually doing anything but makes them feel better.
Just don’t out your art to public if you don’t want someone/thing learn from it. The clinging to relevance and this pompous self importance is so cringe. So replacing blue collar work is ok but some shitty drawings somehow have higher ethical value?
“Just don’t make a living with your art if you aren’t okay with AI venture capitalists using it to train their plagiarism machines without getting permission from you or compensating you in any way!”
If y’all hate artists so much then only interact with AI content and see how much you enjoy it. 🤷♂️
It has nothing to do with AI venture capitalists. Also not every profession is entitled to income, some are fine to remain as primarily hobbies.
AI art is replacing corporate art which is not something we should be worried about. Less people working on that drivel is a net good for humanity. If can get billions of hours wasted on designing ads towards real meaningful contributions we should added billions extra hours to our actual productivity. That is good.
using it to train their plagiarism machines
That’s simply not how AI works, if you look inside the models after training, you will not see a shred of the original training data. Just a bunch of numbers and weights.
It has literally nothing to do with plagiarism.
Every artist has looked at other art for inspiration. It’s the most common thing in the world. Literally what you do in art school.
The idea that you would actually object to replacing labor with automation, but think replacing art with automation is fine, is genuinely baffling.
Except the “art” ai is replacing is labor. This snobby ridiculous bullshit that some corporate drawings are somehow more important than other things is super cringe.
Right, if you post publicly, expect it to be used publicly
Yeah, no. There’s a difference between posting your work for someone to enjoy, and posting it to be used in a commercial enterprise with no recompense to you.
Are you actually suggesting that if I post a drawing of a dog, Disney should be allowed to use it in a movie and not compensate me?
This doesn’t actually work. It doesn’t even need ingestion to do anything special.
Let’s say you draw cartoon pictures of cats.
And your friend draws pointillist images of cats.
If you and your friend don’t coordinate, it’s possible you’ll bias your cat images to look like dogs in the data but your friend will bias their images to look like horses.
Now each of your biasing efforts become noise and not signal.
Then you need to consider if your are also biasing ‘cartoon’ and ‘pointillism’ attributes as well, and need to coordinate with the majority of other people making cartoon or pointillist images.
When you consider the number of different attributes that need to be biased for a given image and the compounding number of coordinations that would need to be made at scale to be effective, this is just a nonsense initiative that was an interesting research paper in lab conditions but is the equivalent of a mouse model or in vitro cancer cure being taken up by naturopaths as if it’s going to work in humans.
Let’s see how long before someone figures out how to poison, so it returns NSFW Images
You can create NSFW ai images already though?
Or did you mean, when poisoned data is used a NSFW image is created instead of the expected image?
Definitely the last one!
companies would stumble all over themselves to figure out how to get it to stop doing that before going live. source: they already are. see bing image generator appending “ethnically ambiguous” to every prompt it receives
It can only target open source, so it wouldn’t bother corpos at all. The people behind this object to not everything being owned and controlled. That’s the whole point.
The Nightshade poisoning attack claims that it can corrupt a Stable Diffusion in less than 100 samples. Probably not to NSFW level. How easy it is to manufacture those 100 samples is not mentioned in the abstract
So it sounds like they are taking the image data and altering it to get this to work and the image still looks the same just the data is different. So, couldn’t the ai companies take screenshots of the image to get around this?
Not even that, they can run the training dataset through a bulk image processor to undo it, because the way these things work makes them trivial to reverse. Anybody at home could undo this with GIMP and a second or two.
In other words, this is snake oil.
Fighting the uphill battle to irrelevance …
The general term for this is adveesarial input, and we’ve seen published reports about it since 2011 when ot was considered a threat if CSAM could be overlayed with secondary images so they weren’t recognized by Google image filters or CSAM image trackers. If Apple went through with their plan to scan private iCloud accounts for CSAM we may have seen this development.
So far (AFAIK) we’ve not seen adversarial overlays on CSAM though in China the technique is used to deter trackng by facial recognition. Images on social media are overlaid by human rights activists / mischief-makers so that social media pics fail to match secirity footage.
The thing is like an invisible watermark, these processes are easy to detect (and reverse) once users are aware they’re a thing. So if a generative AI project is aware that some images may be poisoned, it’s just a matter of adding a detection and removal process to the pathway from candidate image to training database.
Similarly, once enough people start poisoning their social media images, the data scrapers will start scaning and removing overlays even before the database sets are sold to law enforcement and commercial interests.
Data poisoning isn’t limited to just AI stuff and you should be doing it at every opportunity.
if it would work lol
Feeding garbage to the garbage. How fitting.
gaiussabinus@lemmy.world 11 months ago
This system runs on the assumption that A) massive generalized scraping is still required B) You maintain the metadata of the original image C) No transformation has occurred to the poisoned picture prior to training(Stable diffusion is 512x512). Nowhere in the linked paper did they say they had conditioned the poisoned data to conform to the data set. This appears to be a case of fighting the last war.
sukhmel@programming.dev 11 months ago
It is likely a typo, but “last AI war” sounds ominous 😅