How does DeepDetector work?
Cloud-based
Access our ready-to-use technology by using our customisable APIs to integrate DeepDetector into your current workflow.
Protected and compliant
All forms of analyses take place in accordance with European laws and regulations regarding data protection, privacy, and responsible AI.
Representative
Trained with the largest scientific or self-made representative datasets to capture significant information input more efficiently than any other algorithm.
What kind of deepfakes can DeepDetector detect?
Deepfake technology manipulated media
DeepDetector filters all kinds of FaceSwaps and other AI-manipulations by looking for traces of alterations in existing (camera-made) pictures and videos.
Synthetic media and AI-generated deepfakes
AI-generated visual content, such as StyleGANs are not distinguishable for the unaided human eye. DeepDetector analyses characteristics of AI-generated content to detect them.
Facts about DeepDetector
1 Sec
Image analysis time
100%
Explainable results
10+
Deepfake types can be detected
92-99.9% Performance
92.93%
ACCURACY
Percentage of correct predictions (of both real and fake)
84.37%
Precision
Percentage of fake classifications that were actually fake
92.57%
recall
Percentage of actual fakes that are correctly predicted
About DeepDetector
DeepDetector is a deep learning network designed and trained to recognise AI-generated or AI-manipulated faces. DeepDetector can be seen as an artificial neural network designed to spot forgeries and traces generated by computers.
It is able to do this, because the DeepDetector has seen hundreds of thousands of real and deepfake images. It has trained itself on these images and has learned to find the subtle differences between a photo made with a real camera or a photo synthesised by a computer.
You can learn more about it here!
