Real vs. fake: Can you spot AI-generated images?

Three of these images are fake. Can you spot the real image?
Some images generated by artificial intelligence have become so convincingly real that there is no surefire way to spot the fakes. But experts say there are still things we can try to detect fakes.
“Media literacy is super awesome,” said Matt Groh, assistant professor at Northwestern University. “But it needs to extend to AI literacy. Like the classic kind of things that you want to teach in media literacy, we still need to teach those same things. We just need to add the AI portion to it now.”
Groh’s team at Northwestern
on how to spot AI generated images. The
was released in June.
“So what we’ve done is we’ve articulated 5 different categories of artifacts, implausibilities,” Groh said. “Ways to tell AI-generated image apart from a real photograph.”
The academic preprint guide offers detailed tips, tricks and examples on spotting AI-generated images. It also teaches important questions to consider when consuming media.
The first and easiest telltale signs: anatomical implausibilities.
Ask yourself: Are the fingers, eyes, and bodies off? Are there extra limbs or do they bend strangely? Are there too many teeth?
Ask yourself: Do images seem plastic, glossy, shiny or cartoonish? Are there overly dramatic or cinematic?
Ask yourself: Is text garbled? Is clothing strange? Are objects not physically correct, like how this backpack strap merges into clothing?
Ask yourself: Are light and shadows off? Are there impossible reflections?
Ask yourself: Are there images that are just too unbelievable or historically inaccurate?
“What we’re trying to do is give you a snapshot of what it looks like in 2024 and how we can help people move their attention as effectively as possible,” Groh said.
“Education is really the biggest thing. There’s education on the tools,” said Cole Whitecotton, senior professional research associate at the National Center for Media Forensics.
Whitecotton encourages the public to educate themselves and try AI tools to know their capabilities and limits.
“I think everybody should go out and use it. And look at how these things do what they do and understand a bit of it,” he said. “Everyone should interact with ChatGPT. In some way. Everyone should interact with Midjourney. And look at how these things do what they do and understand a bit of it.”
Whitecotton suggests being inquisitive and curious when scrolling through social media.
“If you interacted with every piece of content in that way, then there you would be a lot less likely to be duped and to be sort of sucked into that sort of stuff, right?” he said.
“How do you interact with Facebook and with Twitter and all these things? How do you consume the media?” Whitecotton added.
While AI-generated images and videos continue to evolve, Groh and his team offer a realistic approach to a changing technological landscape where tips and tricks may become outdated quickly.
“I think a real, good, useful thing is we build this. We update this every year. Okay, some of these things work. Some of these things don’t. And I think once we have a base, we’re able to update it,” Groh said. “I think one of the problems is we didn’t have a base. And so one of the things we’re really excited about is even sharing our framework, because I think our framework is going to help people just navigate that conversation.”
So were you able to guess which image is real?
If you guessed the image of the girl in the bottom left corner, you are correct!
“It sucks that there’s this misinformation in the world. But it’s also possible to navigate this new problem,” Groh said.
If you want to test yourself even more, the Northwestern University research team has released
that gives you a series of real and AI-generated images to differentiate.