Shamil Magomedov, head of the Intelligent Information Security Systems Division at RTU MIREA Institute for Cyber Security and Digital Technologies, told RT how to determine if a photo was produced by a neural network.
The expert underlines that first of all, attention should be paid to the visual format. A significant proportion of neural networks create “headshot photos” with close-up faces and almost no background. The second is with blurry and poorly tracked details.
The expert noted that the proportions of the face drawn by artificial intelligence are almost ideal and are prone to the golden ratio, unlike real faces with asymmetry.
Magomedov believes that neural networks are not successful at all on human limbs – they draw an odd number of fingers, pointing the hands in an unnatural position. In addition, it is almost impossible to determine the expression of the eyes in the created photos – the person’s gaze seems blurred and out of focus.
Finally, the expert urged to pay attention to the small details – the more details, the more likely the photo was actually taken.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
