Improved Homomorphically Encrypted Biometric Identification Using Coefficient Packing

Pia Bauspies, Jonas Olafsson, Jascha Kolberg, Pawel Drozdowski, Christian Rathgeb, Christoph Busch

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

Efficient large-scale biometric identification is a challenging open problem in biometrics today. Adding biometric information protection by cryptographic techniques increases the computational workload even further. Therefore, this paper proposes an efficient and improved use of coefficient packing for homomorphically protected biometric templates, allowing for the evaluation of multiple biometric comparisons at the cost of one. In combination with feature dimensionality reduction, the proposed technique facilitates a quadratic computational workload reduction for biometric identification, while long-term protection of the sensitive biometric data is maintained throughout the system. In previous works on using coefficient packing, only a linear speed-up was reported. In an experimental evaluation on a public face database, efficient identification in the encrypted domain is achieved on off-the-shelf hardware with no loss in recognition performance. In particular, the proposed improved use of coefficient packing allows for a computational workload reduction down to 1.6% of a conventional homomorphically protected identification system without improved packing.

Original languageEnglish
Title of host publicationProceedings of 2022 International Workshop on Biometrics and Forensics
Number of pages6
PublisherIEEE
Publication date2022
ISBN (Electronic)9781665469623
DOIs
Publication statusPublished - 2022
Event2022 International Workshop on Biometrics and Forensics - Salzburg, Austria
Duration: 20 Apr 202221 Apr 2022

Conference

Conference2022 International Workshop on Biometrics and Forensics
Country/TerritoryAustria
CitySalzburg
Period20/04/202221/04/2022

Keywords

  • Biometric identification
  • Biometric information protection
  • Computational workload reduction
  • Homomorphic encryption

Fingerprint

Dive into the research topics of 'Improved Homomorphically Encrypted Biometric Identification Using Coefficient Packing'. Together they form a unique fingerprint.

Cite this