COM-PRESS

Fact checking manipulated images is particularly challenging

Disinformation and misinformation is a growing problem for our society since the rise of social media. Images and videos are spread and viewed at a rapid pace, without guarantees on their authenticity. To address this, independent news media conduct fact checks in which they check and refute viral messages. Despite news organisations’ vast baggage of experience and knowledge, detecting manipulations made with sophisticated techniques is extremely difficult.

Bringing fundamental research of image manipulation detection to the press

The COM-PRESS research project developed detection methods that journalists can use to detect and debunk image manipulations. It investigated new, promising techniques that look deeper than what can be seen with the naked eye. The COM-PRESS consortium further explored these techniques in fundamental research, while bridging the gap to socially relevant use cases.

Specifically, COM-PRESS worked towards the following objectives:

• Investigating the credibility of existing manipulation techniques.
• Developing new detection methods of image manipulations, as well as searching for complementary detection methods.
• Opening up detection methods to journalists and evaluating them in concrete use cases.

In this way, COM-PRESS created new insights in disinformation, in order to increase the resilience of citizens and journalists against disinformation.

The research consortium

The research groups IDLab-MEDIA (imec-UGent) and imec-mict-UGent joined forces with Apache (De Werktitel) as media partner. The consortium also worked to develop a dashboard. The project ran from October 2022 to June 2024, with subsidies from the Flemish government’s Department of Culture, Youth & Media (Departement Cultuur Jeugd & Media).