An approach for verifying terrestrial photographs via geosignatures
Authors/Creators
-
1.
University of Münster
- 2. CODECHECK
Description
With the widespread availability of generative AI, it is now possible to create images that resemble photographs taken at real locations. This makes it harder to use photographs as reliable evidence for assessing the state of the world at a particular location and time. To address this, we designed an approach to cryptographically bind a photograph to its capture location and time. This geosignature is encoded as a QR code and embedded in the photograph immediately after it is captured. Our approach is intended to support verification of whether an image has been modified after capture, as well as where and when it was taken. We present the approach, a first prototype implementation, and findings from an initial informal user study. The prototype demonstrates the technical feasibility of the approach, while the user study provides preliminary evidence of its usability. We also identify a number of limitations and opportunities for future improvement.
Files
COSIT26_GeoCamFinal.pdf
Files
(1.1 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:798bb3e6a47499d358c5b0f4f3774f68
|
1.1 MB | Preview Download |
Additional details
Software
- Repository URL
- https://github.com/SP3DAG