Damnatio Memoriae: Adversarially and Selectively Forgetting Identities in the Embedding Space of Face Recognition Models
A breakthrough approach for enabling the right to be forgotten within high-stakes facial recognition systems.
A face recognition model links two images of a person recorded on separate occasions when their embedding similarity exceeds an operating threshold. We consider making chosen identities unlinkable across separate occasions while the model remains in service for the rest of the po...
ArXiv CS.CV
Source
Generated insight by OnAirToday AI
This research introduces a critical mechanism for protecting privacy by selectively erasing specific identities from facial recognition models without compromising overall system performance. It marks a significant shift in AI accountability, allowing individuals to effectively opt-out of persistent tracking while the underlying model remains operational.
Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.