We are not able to identify AI-generated images

TL;DR

This study demonstrates that humans have difficulty reliably distinguishing AI-generated images from real photographs, even with simple portrait images, highlighting the need for better detection methods and ethical considerations.

Contribution

It provides empirical evidence that humans struggle to identify AI-generated images, emphasizing the limitations of human judgment in the face of advancing synthetic media.

Findings

Humans achieved only 54% accuracy in identifying AI images.

Response times averaged 7.3 seconds, indicating difficulty and uncertainty.

Some images remained consistently deceptive across users.

Abstract

AI-generated images are now pervasive online, yet many people believe they can easily tell them apart from real photographs. We test this assumption through an interactive web experiment where participants classify 20 images as real or AI-generated. Our dataset contains 120 difficult cases: real images sampled from CC12M, and carefully curated AI-generated counterparts produced with MidJourney. In total, 165 users completed 233 sessions. Their average accuracy was 54%, only slightly above random guessing, with limited improvement across repeated attempts. Response times averaged 7.3 seconds, and some images were consistently more deceptive than others. These results indicate that, even on relatively simple portrait images, humans struggle to reliably detect AI-generated content. As synthetic media continues to improve, human judgment alone is becoming insufficient for distinguishing real from artificial data. These findings highlight the need for greater awareness and ethical guidelines as AI-generated media becomes increasingly indistinguishable from reality.