Other nomination
Abusing Intended Feature And Bypassing Facial Recognition.pptx
An app's signup requires a live face-detection step, with only two criteria: the face must be human and looking straight ahead. Testing shows a physical photograph held to the camera blurs and is rejected, but a deepfake image supplied through the app's own intended gallery-import feature satisfies both criteria and passes, so anyone can verify as the account holder without ever being in front of the camera.
Record
- Researcher
- Ishwar Kumar
- Format
- Slides
In the archive
Tags
This page is the archive's own catalogue record. The research is the work of Ishwar Kumar, first published at the original source. Preserved copies are kept so the citation survives its host.