Checking the Authenticity of Media Data
CRISP researchers at the Fraunhofer SIT analyze the Ibiza video for manipulations
On behalf of SPIEGEL and Süddeutsche Zeitung, CRISP scientist Prof. Dr. Martin Steinebach’s team at Fraunhofer SIT checked the authenticity of the Ibiza video, the release of which led to the resignation of the Austrian Vice Chancellor Strache. The Federal Ministry of Research and the Hessian Ministry of Science support the research and development of technological tools for manipulation detection on a large scale.
Manipulations in Medien Data
Digital multimedia data are a pillar of fact-based reporting in today’s media world. However, only simple means are necessary to tamper with or modify such media data. Fraunhofer SIT is offering a wide portfolio of services and tools to detect manipulations. One challenge in doing so is the efficient inspection of large media data sets, as they often occur in forensic investigations. In addition, media data often contain many invisible traces.
If someone would like to “put words into the mouth” of a specific person and when there is sufficient audio material of that person, a computer can be ”taught to speak with any voice“ desired. These ”deep fakes“ on a ”soundtrack“ can be detected, just like manipulations by ”audio editors“.
Images are easy to manipulate, but each change leaves its mark. Our processes and algorithms recognize these discrepancies and indicate tampering. We also examine the meta data, verify the cameras a data source (“camera ballistics“) and search for comparative image material in the Internet. Further research leads us to evidence of anti-forensics, i. e. attempts to obscure the manipulations.
To detect video manipulations the material is first checked and correlated with regard to its technological meta data. Do the segments established as temporally aligned really match? Is there a temporal offset or gap? Do segments repeat? The individual elements may be analyzed as well. This allows checking whether contents exhibit unusual cracks caused by cuts. To do this, we review the noise of the data and behavior of the sound, for example.
Disinformation (fake news) refer to publications that are demonstrably factually wrong or misleading and published with a manipulative intent. In the DORIAN project we are developing semi-automated to fully automated detection techniques for fake news.