Alphabet’s (NASDAQ: GOOGL) Jigsaw division has unveiled a free tool that could help journalists identify doctored photographs. Doctored and misleading images are becoming more common as disinformation and targeted campaigns have proliferated on the internet. It is not always easy to tell the difference between real and fake photographs leading newsrooms, fact-checkers, and journalists to be especially wary of publishing images that are difficult to quickly verify.
The free tool, called Assembler, helps users sort out real images from fake ones. It has been trained to identify several ways that photos or media are doctored by various detection models contributed by Jigsaw’s academic partners. The tool can analyze an image and highlight where traces of changes may have been left behind.
Jared Cohen, Jigsaw’s chief executive, said, “Assembler brings together multiple image manipulation detectors from various academics into one tool, each one designed to spot specific types of image manipulations. Individually, these detectors can identify very specific types of manipulation—such as copy-paste or manipulations to image brightness. Assembled together, they begin to create a comprehensive assessment of whether an image has been manipulated in any way.”
Assembler’s detectors can identify things like an image pasted over another or changes to image brightness. It can also detect color pattern anomalies and where areas of an image have been copied and pasted several times. One of the detectors can determine whether more than one camera model was used to create an image. Another was designed to identify “deepfakes,” realistic images that have been heavily manipulated by artificial intelligence.
Five of the Assembler’s image detectors were developed by research teams at universities. The other two detectors were developed by Jigsaw. The company is now testing the tool with more than a dozen news and fact-checking organizations around the world. Jigsaw does not currently plan to offer the tool to the public.