Duped by Photoshop: People Are Bad at Spotting Fake Photos

Study tests people's ability to detect manipulated images of real-world scenes.

Follow us onFollow Tech Explorist on Google News

In social media, many people upload fake photos. Even, many people assumed that these fake photos are real. A new study can tell why some people are bad at spotting fake photos. Scientists examined why doctored images can fool so many people.

To observe, scientists collected 10 original photos depicting people in real-world scenes. They then doctored them in various ways, creating a photo bank of 30 fake photos. While doing that scientists smartly made some physically implausible changes. For example, changing the direction of a shadow or distorting the angles of buildings.

They involved almost 700 participants and asked them to identify each photo if digitally altered. Participants never saw the same photo twice.

During the study, scientists showed a number of real and fake images to participants, They then asked them for spotting fake photos. Participants did it with 60% accuracy, that would be expected by chance.

When scientists asked participants to pinpoint what’s wrong with the photo, they correctly showed the edited portion of the image.

Scientists said, “Participants tended to be better at identifying physically implausible manipulations than physical plausible ones. For example, when a shadow was manipulated, participants correctly identified the photo as fake about 60 percent of the time, but when the photo was airbrushed, participants were able to identify the fake photos only about 40 percent of the time.”

Study co-author Derrick Watson, also of the University of Warwick said, “Even though people are able to detect [that] something is wrong, they can’t reliably identify what exactly is wrong with the image. Images have a powerful influence on our memories, so if people can’t differentiate between real and fake details in photos, manipulations could frequently alter what we believe and remember.”

Now, scientists are finding the way of detecting fake photos with the naked eye. For example, it may be possible to train people to notice when photos defy the laws of nature.

In the next experiment, scientists asked participants to look more closely. This time researchers divided images into 12 sections. They then asked people to locate the section that was altered, regardless of whether the individuals originally thought the image had been altered. This time, participants performed better on this task. They pin point the doctored portion of the photo 56 percent of the time.

Nightingale said, “The challenge now is to try to find ways to help people improve at this task of spotting fake photos. We’re conducting new research to see whether people can make use of [Telltale] signs to help identify forgeries.”

Examples of the original and manipulated images used in the study can be found here.