Not likely to be AI-generated or Deepfake

I mean, it could be a manual photoshop job. Just because it’s not AI doesn’t mean it’s real.

But also the detector is probably wrong - it’s likely an AI image using a different model than the detector was trained to detect.

There were a lot of really good images like that well before AI. Anyone remember Photoshop Friday?
- There's a sort of... Sheen, to a lot AI images. Obviously you can prompt this away if you know what you're doing, but its developing a bit of a look to my eye when people don't do that.
- Can we bring that back?
- The shell looks ai generated though, if it was photoshopped it would've been a snail shell used for the source image.
I mean, it could be a manual photoshop job.
It could, but the double spiral in the shell indicates AI to me. Snail shells don't grow like that. If it was a manual job, they would have used a picture of a real shell.
Edit: plus the cat head looks weird where it connects to the head, and the markings don't look right to me.
- Agreed. The aggressive depth of field is another smoking gun that usually indicates an AI image.
- Snail shells don't grow like that but this is clearly a snat, not a snail.
- Also the fact that the grain on the side of the shell is perpendicular to the grain on the top, and it changes where the cat ear comes up in front of it.
  Very telltale sign of AI is a change of pattern in something when a foreground object splits it.
  Not saying it's always a guarantee, but it's a common quirk and it's pretty easy to identify.

…you know people made fake pictures before image generation, right?

They made fake pictures before computers existed too.
- This obviously can’t be true, how did they do it without Photoshop? /s
- I've seen the cave paintings deer and horses everywhere but when I look around nothing but rocks and trees.

"We investigated ourselves and found nothing wrong."

Back2thefuture_iknowthisone.png
That's a song by the police, right?
- Iseewhatyoudidthere.jpg
  LOL

Miao

Ignorant Americans, never even heard of the common snailcat

Where the fuck are you from that they aren’t called catsnails? Odd. Been catsnails here since I can remember.

Check the snail house. The swirl has two endings. Definitely AI
Or maybe your expectations from ai detection are too high.

I have two of those cats. I still can't catch them when its time to go to bed.

No spooky eyes, no extra limbs, no eery smile? - 100% real, genuine photograph! 👍

It's a snat. They are not easy to catch, because they are fast. Also, they never land on their shell.

cute snat...

That's clearly a cail
- Are we all looking at the same snussy?
We get them a lot around here. They don't make for good pets, but they keep the borogoves at bay.
- Which is great, honestly. Borogoves themselves are fine, but it's not worth the risk letting them get all mimsy.

I wanted to get a cat but I discovered I was allergic to the slime trail.

Such a cute kitty snail! Can you post just the picture?

Its an "AI generated image at snail" :3
Detection for snail is positive.

yeah just shopped

It's not, look at the shell

That's a normal housecat. Not sure what people are confused about

Chat is the picture real?

It's a real valid picture in png format.
HAS SCIENCE GONE TO FAR?!
Oui, biensur!

Clearly AI is on the verge of taking over the world.

Well duh it detects AI generated images that are at scale and that snail cat is way too small for it

That is a weird looking rabbit

It has been 0 days since classified military gene research has been leaked by interrogating ai detecting models

My guess is the AI was trained on a combination of cat videos and sponge bob.

honestly, its pretty good, and it still works if I use a lower resolution screenshot without metadata (I haven't tried adding noise, or overlaying something else but those might break it). This is pixelwave, not midjourney though.

So only 2% "not likely to be AI-generated or deepfake"... that means that it's almost definitely AI, got it!? :-P

Not unclear as a whistle.

There are a bunch of reasons why this could happen. First, it's possible to "attack" some simpler image classification models; if you get a large enough sample of their outputs, you can mathematically derive a way to process any image such that it won't be correctly identified. There have also been reports that even simpler processing, such as blending a real photo of a wall with a synthetic image at very low percent, can trip up detectors that haven't been trained to be more discerning. But it's all in how you construct the training dataset, and I don't think any of this is a good enough reason to give up on using machine learning for synthetic media detection in general; in fact this example gives me the idea of using autogenerated captions as an additional input to the classification model. The challenge there, as in general, is trying to keep such a model from assuming that all anime is synthetic, since "AI artists" seem to be overly focused on anime and related styles...

So the prophecy is fulfilled

Honestly, they should fight fire with fire? Another vision model (like Qwen VL) would catch this

You can ask it "does this image seem fake?" and it would look at it, reason something out and conclude it's fake, instead of... I dunno, looking for smaller patters or whatever their internal model does?

What tool is this? I assume the tool is also AI based?

You have never seen the all elusive catsnail? Bummer you should look harder.

Isn't there a whole thing about if you average out colors on AI generated photos you get a uniform ~~beige~~ grey toned color? As the brightness is usually about 50/50 from the original noise map. (Added in for the people who I confused with colors)

I don't get why these tools don't just do that but I guess you got to keep the marketing up of using AI to find a solution.

Either that’s not true of AI images or it’s true of all images. There aren’t answers that simple to this. Pixels are pixels.
- It is absolutely not true of all AI images. I'd be surprised if it's even true about most AI images.
- What? That's some extreme logic.
  First of all why would it be true of all images? Real photos would have variance of contrast and color in different ways.
  These guys literally point out average colors and contrast in AI images
  Instead of engaging the conversation you just say pixels are pixels? Like that means something smart?