mlsanityData to 7 Oct 2026

Is it Possible to Generate Irreversible PolyProtected Templates from Face Embeddings using System-Specific Keys?

arXiv 2610.01385 ↗First posted 1 Oct 2026cs.CR cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

This work aims to answer the question of whether it is possible to generate irreversible protected templates when the PolyProtect biometric template protection method is applied to face embeddings using system-specific keys (i.e., the same C and E parameters, which define the transform, are applied to all subjects' face embeddings), instead of the traditional subject-specific keys (i.e., each subject has their own C and E parameters). This is important for determining whether we can perform de-duplication of face identities in the PolyProtected domain, which is not possible in the subject-specific key scenario due to the clash with PolyProtect's unlinkability property (i.e., one could generate multiple protected templates belonging to the same identity, using different C and E parameters, such that those templates cannot be linked to each other). We present experiments (reproducible using our open-source code) to prove that there exist at least three ways of systematically selecting system-specific keys that produce irreversible PolyProtected templates: (i) from pre-selected subject-specific keys, (ii) by applying a previously proposed key selection algorithm to random vectors, and (iii) by approximating a "good" C/E pair distribution from which system-specific keys can be constructed. Our findings thus point to the conclusion that it is, indeed, possible to safely operate PolyProtect in the system-specific key scenario without degrading the template protection potential. This opens up the possibility for identity de-duplication in the PolyProtected domain.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 15 of its 30 references that are in the map. First posted on arXiv 1 Oct 2026.

Builds on

15 of 30 references.

References · 15

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  3. 2017On the Reconstruction of Face Images from Deep Face Templatescited by 66
  4. 2017Synthesizing Normalized Faces from Facial Identity Featurescited by 33
  5. 2023EdgeFace: Efficient Face Recognition Model for Edge Devicescited by 33
  6. 2018Secure Face Matching Using Fully Homomorphic Encryptioncited by 29
  7. 2020HERS: Homomorphically Encrypted Representation Searchcited by 26
  8. 2020Beyond Identity: What Information Is Stored in Biometric Face Templates?cited by 23
  9. 2016Inverting face embeddings with convolutional neural networkscited by 22
  10. 2021Towards Protecting Face Embeddings in Mobile Face Verification Scenarioscited by 14
  11. 2021Deep Face Fuzzy Vault: Implementation and Performancecited by 12
  12. 2019Zero-Shot Deep Hashing and Neural Network Based Error Correction for Face Template Protectioncited by 9
3 more
  1. 2024in-Car Biometrics (iCarB) Datasets for Driver Recognition: Face, Fingerprint, and Voicecited by 2
  2. 2025Securing Face and Fingerprint Templates in Humanitarian Biometric Systemscited by 2
  3. 2026A Deeper Dive into the Irreversibility of PolyProtect: Making Protected Face Templates Harder to Invertcited by 1

Built on by

Not cited yet.