People are overconfident about spotting AI faces, study finds

Can you tell which three of the face images above are AI-generated and which face is 'real'? The answer is at the bottom of this page.

Most people believe they can spot AI-generated faces, but advances in technology mean it's becoming harder to tell what's real and what's not, research from UNSW Sydney and The Australian National University (ANU) has demonstrated.

"Up until now, people have been confident of their ability to spot a fake face," Dr James Dunn from UNSW Sydney said.

"But the faces created by the most advanced face-generation systems aren't so easily detectable anymore."

The researchers asked 125 participants - including 36 people with exceptional face-recognition ability, known as 'super-recognisers', and 89 control participants - to complete an online test in which they were shown a series of faces and asked to judge whether each image was real or AI-generated.

Obvious visual flaws were screened out beforehand. The research team published their findings in the British Journal of Psychology.

"What we saw was that people with average face-recognition ability performed only slightly better than chance," Dr Dunn said.

"And while super-recognisers performed better than other participants, it was only by a slim margin. What was consistent was people's confidence in their ability to spot an AI-generated face - even when that confidence wasn't matched by their actual performance."

The end of artefacts

Much of that confidence comes from cues that used to work. Early AI-generated faces were often given away by obvious visual artefacts - distorted teeth, glasses that merged into faces, ears that didn't quite attach properly, or strange backgrounds that bled into hair and skin.

But as face-generation systems have improved, those kinds of errors have become far less common. The most realistic outputs no longer show obvious flaws, leaving faces that look convincing at a glance, and far harder to judge using the cues people are familiar with.

"A lot of people think they can still tell the difference because they've played with popular AI tools like ChatGPT or DALL·E," ANU Associate Professor Amy Dawel said.

"But those examples don't reflect how realistic the most advanced face-generation systems have become, and relying on them can give people a false sense of confidence."

What interested the researchers was how readily even super-recognisers were fooled. While this group did perform better on average, the advantage was modest, and their accuracy remained far below what they typically achieved when recognising real human faces.

There was also substantial overlap between groups, with some non-super-recognisers outperforming super-recognisers - demonstrating this is not simply an experts-versus-everyone-else problem.

Too good to be true

But if AI faces are this convincing, are there any tells we should be looking for?

"Ironically, the most advanced AI faces aren't given away by what's wrong with them, but by what's too right," Associate Professor Dawel said.

"Rather than obvious glitches, they tend to be unusually average - highly symmetrical, well-proportioned and statistically typical."

Qualities such as symmetry and average proportions usually signal attractiveness and familiarity. But in the current study, they become a red flag for artificiality.

"It's almost as if they're too good to be true as faces," Associate Professor Dawel said.

What to do about it

Super-recognisers didn't stand out the way they typically do in tests involving real human faces, showing only a modest advantage. What differentiated them was a greater sensitivity to the same qualities identified in the study - plausible, unusually average and highly symmetrical faces. Even so, their limited success suggests spotting AI faces is not a skill that can be easily trained or learned.

The findings also carry practical implications, as relying on visual judgement alone is no longer reliable. This matters in contexts ranging from social media and online dating to professional networking and recruitment, where people often assume they can 'just tell' when a profile picture looks fake.

Misplaced confidence may leave individuals and organisations more vulnerable to scams, fake profiles and fabricated identities.

"There needs to be a healthy level of scepticism," Dr Dunn said.

"For a long time, we've been able to look at a photograph and assume we're seeing a real person. That assumption is now being challenged."

Rather than teaching people tricks to spot synthetic faces, the broader lesson is about updating assumptions. The visual rules many of us rely on were shaped by earlier, less sophisticated systems.

"As face-generation technology continues to improve, the gap between what looks plausible and what is real may widen - and recognising the limits of our own judgement will become increasingly important," Associate Professor Dawel said.

Looking ahead

Interestingly, Dr Dunn wonders whether the research team has stumbled upon a new kind of face recogniser.

"Our research has revealed that some people are already sleuths at spotting AI-faces, suggesting there may be 'super-AI-face-detectors' out there," Dr Dunn said.

"We want to learn more about how these people are able to spot these fake faces, what clues they are using, and see if these strategies can be taught to the rest of us."

Good with faces? Visit the UNSW Face Test page where you can test your face recognition skills and see if you can spot the AI-faces in a free demo of the AI faces task used in the above research.

The study has been published in the British Journal of Psychology.