Thursday, July 22, 2004

What's Next: For Doctored Photos, a New Flavor of Digital Truth Serum

The New York Times > Technology > Circuits > What's Next: For Doctored Photos, a New Flavor of Digital Truth Serum:
"'It used to be that you had a photograph, and that was the end of it - that was truth,' said Hany Farid, an associate professor of computer science at Dartmouth College who is a leader in the field. 'We're trying to bring some of that back. To put some measure of guarantee back in photography.'

At stake is more than the fate of possible child pornographers. The United States military has become increasingly reliant on digital images from drones and satellites to give soldiers a sense of the battlefield. Law enforcement officers routinely use digital cameras to photograph crime scenes. Newspapers and magazines are now dependent on digital photographs that can be easily doctored.

Over the last three years, Professor Farid and his students have become experts at forgery, making hundreds of images that look authentic but have in fact been digitally tweaked. License plate numbers are changed. A single stool standing on a checkerboard floor is suddenly a pair of stools. Dents on a car are wiped away with a few mouse clicks.

The skillful tampering disturbed the images in ways that the human eye could not detect. But Professor Farid says his algorithms can spot them and sound the alarm."

For example, when two images are spliced together - like the picture of a shark attacking a helicopter that has circulated around the Internet in the past few years - one or both of the original pictures usually has to be shrunk, enlarged or rotated to make the pieces fit together. And those changes, no matter how artful, leave clues behind.

Take a picture that is 10 pixels by 10 pixels, for a total of 100. Stretch it to 10 by 20 pixels, and image-editing software like Adobe Photoshop will assign the picture's original pixels to every other slot in the new picture. That leaves 100 pixels "blank," or without values. Image-editing software fills in the gaps by examining what their neighbors look like, and then applying an average. To oversimplify, if pixel A is blue, and pixel C is red, the blank pixel B will become purple.

This kind of averaging becomes "pretty obvious" after some analysis of the image, Professor Farid said.

In tests on several hundred doctored photos, this technique for detecting changes proved to be virtually foolproof if the picture quality was high enough. Uncompressed TIFF image files, which contain enormous amounts of data, were like an open book to Professor Farid's team.

But Professor Farid said that for now the technique does not work as well with files created in JPEG, the compressed picture format most commonly used online.
con·cept: What's Next: For Doctored Photos, a New Flavor of Digital Truth Serum