{"id":6690,"date":"2020-12-04T16:19:00","date_gmt":"2020-12-04T16:19:00","guid":{"rendered":"https:\/\/bernhardrinner.com\/?p=6690"},"modified":"2020-12-09T13:50:54","modified_gmt":"2020-12-09T13:50:54","slug":"3sat-nano-reports-about-our-privacy-protection-research","status":"publish","type":"post","link":"https:\/\/bernhardrinner.com\/?p=6690","title":{"rendered":"Privacy-protection research in 3sat science show nano"},"content":{"rendered":"\n

Our research on privacy-protection in cameras and in drone videos was broadcasted across Germany, Switzerland, and Austria. The science show nano<\/a> from 3sat reported about our TrustEYE prototype for protection onboard cameras and our video anonymization in aerial videos.<\/p>\n\n\n\n

\"\"<\/a>
Click on image to start the video<\/figcaption><\/figure>\n\n\n\n
\n
\n
\"\"
TrustEYE (2014)<\/figcaption><\/figure>\n<\/div>\n\n\n\n
\n

The key idea of TrustEYE <\/strong>is to protect<\/em> access to the image sensor and encapsulate dedicated security and privacy functionality in a secure sensing unit embedded on the camera. The TrustEYE has exclusive access to the image sensor\u2019s raw data. It separates sensitive from non-sensitive data by applying dedicated image analysis and ensures that only non-sensitive data is available to the camera host system.<\/p>\n<\/div>\n<\/div>\n\n\n\n

Our video anonymization<\/strong> is based a robust spatio-temporal hopping blur filter<\/em> that protects privacy through de-identification of face regions. The filter distorts a face region with secret parameters to be robust to na\u00efve, parrot and reconstruction attacks. The distortion is minimal and adaptive to the resolution of the captured face. This privacy filter produces temporally smooth and pleasant videos.<\/p>\n\n\n\n

\n