Reliably detecting and clearly explaining deepfake images
3 Articles
3 Articles
Reliably detecting and clearly explaining deepfake images
Artificial intelligence can now generate images that are virtually indistinguishable from real ones. Researchers at the Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB have developed RealOrRender, a tool that not only specifically detects such deepfakes but also explains why an image is classified as real or AI-generated. The new hybrid approach significantly improves detection accuracy, while explainable AI pr…
The Fraunhofer Institute for Optronics, System Technology and Image Evaluation, together with the Federal Office for Information Security, has developed a method for detecting AI-generated images. According to the research institute, the project "RealOrRender" is not only intended to distinguish deepfakes from real images, but also to make clear which features led to the respective evaluation.
Artificial intelligence is now generating images that can hardly be distinguished from real ones. With RealOrRender, researchers at the Fraunhofer Institute for Optronics, System Technology and Image Evaluation IOSB have now developed a process that not only specifically detects such deepfakes, but also makes it understandable why an image is classified as genuine or AI-generated. The new hybrid approach significantly increases detection accurac…
Coverage Details
Bias Distribution
- 100% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
