Humans are easily fooled by digital images

• Published in: Computers & graphics Vol. 68; pp. 142 - 151
• Main Authors: Schetinger, Victor, Oliveira, Manuel M., da Silva, Roberto, Carvalho, Tiago J.
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01.11.2017; Elsevier Science Ltd
• Subjects: Authenticity; Behavior forensics; Digital image forensics; Digital imaging; Digital media; Forensic engineering; Scientific papers; Digital image forensics; Behavior forensics
• ISSN: 0097-8493; 1873-7684
• DOI: 10.1016/j.cag.2017.08.010

•We tested how good people are at noticing changes on images.•17,280 answers were collected from 383 different volunteers.•Subjects guessed if an image had been changed about half of the times.•We show how subject and image features relate to performance. Digital images are everywhere, from social media to news and scientific papers. This paper describes an extensive user study to evaluate the ability of an average individual to spot edited images. By design, our study avoids lucky guesses. After observing an image, subjects were asked if it is authentic or not. Whenever a subject indicated that an image has been altered, (s)he had to provide evidence to support the answer by pointing at the suspected region in the image. We collected 17,208 individual answers from 393 volunteers, using 177 images selected from public forensic databases. Our results indicate that the average individual is not good at distinguishing original from edited images, answering correctly on 58% of all images, and only identifying the modified ones 46.5% of the time. This performance is superior to random guessing, but poor compared to results achieved by computational techniques. [Display omitted]