Skip to content

Protecting Face Recognition Templates based on Embeddings


We proposed PolyProtect, a method for protecting the sensitive face embeddings that are used to represent people’s faces in neural-network-based face verification systems.

PolyProtect transforms a face embedding to a more secure template, using a mapping based on multivariate polynomials parameterised by user-specific coefficients and exponents.


Krivokuca, V. and Marcel, S. (2022). Towards Protecting Face Embeddings in Mobile Face Verification Scenarios. IEEE Transactions on Biometrics, Behavior, and Identity Science.


PolyProtect can be tuned to achieve a satisfactory trade-off between the recognition accuracy of the PolyProtected face verification system and the irreversibility of the PolyProtected templates. Furthermore, PolyProtected templates are shown to be effectively unlinkable, especially if the user-specific parameters employed in the PolyProtect mapping are selected in a non-naive manner.


  • Face Recognition


A method for protecting biometric templates, and a system and method for verifying a speaker's identity
V. Krivokuca Hahn, S. Marcel
US 11,514,918 / EP 3719679 (ref. IDIAP-11)

Technology Readiness Level



Mapping 128-dimensional V to P for different amounts of overlap using PolyProtect

Contact us for more information

  • Interested in using our technologies?
  • Interested to know more about the licensing possibilities and conditions?

Contact us