Fake faces generated by AI are now "too good to be true," researchers warn
SMRTR summary
Australian researchers found that AI-generated faces have become so realistic that most people can barely detect them, performing only slightly better than random guessing. Even individuals with exceptional face-recognition abilities, known as "super recognizers," showed only marginal improvement in identifying fake faces during tests with 125 participants. The study reveals that modern AI faces lack obvious flaws but instead appear "too perfect" with unusual symmetry and average features, creating security risks as scammers exploit these convincing deepfakes.
SMRTR provides this summary for quick context. The original article belongs to TechSpot.
Read the original article