Bloom filters (BFs) and homomorphic encryption (HE) are prominent techniques used to design biometric template protection (BTP) schemes that aim to protect sensitive biometric information during storage and comparison. In this talk, Amina will discuss the strengths and weaknesses of these two approaches. Her key insight is to extend this theoretical investigation to iris recognition, which 1) benefits from the alignment-free property of BFs and 2) induces huge computational burdens in the HE-encrypted domain. BF-based BTPs can be fast with high recognition accuracy but lack unlinkability, or fast with unlinkability but lack high accuracy. HE-based BTPs are secure, accurate, and unlinkable, but slower than BF-based approaches. In light of a joint work recently published in the IET Biometrics journal in 2022, Amina will present her hybrid BTP scheme that combines BFs and HE as a solution that ensures unlinkability and high recognition accuracy while being seven times faster than the traditional HE-based approach.
Amina Bassit received her BSc degree in discrete mathematics from Hassan II University (2013) and her MSc degree in cryptography from both Mohammed V University and Limoges University (2015). She was employed as a cryptographer at the DGSSI Morocco (2016-2019). Since April 2019, Amina has joined the DMB group and the SCS group of the University of Twente to design a biometric verification protocol in the encrypted domain. In May 2020, Amina started her Ph.D. as part of the PriMa (Privacy Matters) project, where she is investigating the integration of biometric recognition and homomorphic encryption with a special interest in security against malicious adversaries.
We thank our media partner: