Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.22236 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917171824689152 |
|---|---|
| author | Pavão, Adrien |
| author_facet | Pavão, Adrien |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_22236 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | We are not able to identify AI-generated images Pavão, Adrien Artificial Intelligence Machine Learning 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. |
| title | We are not able to identify AI-generated images |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2512.22236 |