Deepfake
AI-generated or altered video, audio or images that imitate a real person.
Deepfakes use machine learning to swap faces, generate faces that don't exist or imitate voices. In identity fraud, they are used to pass selfie and liveness checks with someone else's face or with a face that belongs to nobody.
How deepfakes are used against verification
- Face swaps in a live video, so the selfie matches a stolen ID.
- Generated faces combined with forged documents for synthetic identities.
- Replaying deepfake video through a virtual camera (an injection attack) instead of holding a screen up to the camera.
How they are stopped
No single check is enough. Layered verification makes deepfakes much harder to use: a document whose chip data is genuine, a face that matches it, liveness detection, and checks that the video really comes from the device's camera.
Contact
Talk to us
Tell us what you’re trying to verify. We’ll show you how secuveri can fit your workflow.
