•  
  •  
 

Abstract

The rise of artificial intelligence has led to a surge in AI-generated images, creating new obstacles for forensic investigations. As synthetic images become increasingly realistic, distinguishing them from authentic content becomes more difficult. In forensic investigations, it is essential to prove the authenticity and integrity of digital evidence to maintain admissibility in court. Currently, there are various AI detection tools on the market; however, their accuracy and reliability remain uncertain. This study evaluates the effectiveness of several free AI-generated image-detection tools compared with judgments from unaided college students or recent graduates. Participants were asked to analyze a set of 30 images, 15 authentic and 15 AI-generated, and determine whether they thought it was a real or fake image. They were also asked to rate their confidence in each image on a scale of 0 to 5. Four free AI detection tools were tested on the same dataset, and their performance was compared with that of the participants. The results showed notable differences in human perception and AI detection accuracy. These findings highlight the strengths and limitations of both approaches and assess whether accessible AI detection tools are reliable for forensic use or if human judgment remains essential in identifying synthetic content.

Download

Share

COinS