Approved
Privacy Preserving Biometric Multi-factor Authentication
Emil Gedenryd ()
Start
2023-01-19
Presentation
2023-06-16 14:00
Location:
E:2311
Finished:
2023-07-01
Master's thesis:
Abstract
This thesis investigates the viability of using Fully Homomorphic Encryption and Machine Learning to construct a privacy-preserving biometric multi-factor authen- tication system. The system is based on the architecture described as ”Model K” in ISO/IEC 24745:2022 and uses the TFHE scheme proposed by [1] to encode and compare encrypted fingerprint images. A machine-learning-based encoder is designed using the VGG11 network architecture described by [2]. The encoder is tuned for one-shot classification as a Siamese network to optimize the Euclidean distance between fingerprints from different individuals. The network is then made compatible with TFHE using the Concrete-ml library for Python. Using a prototype of the system, we show that the system succeeds in pre- serving users’ privacy with a relatively high authentication success rate. However, performance benchmarks show that the proposed encoding method is too ineffi- cient. Finally, we highlight some areas of interest for future work that could make a system for privacy-preserving biometric multi-factor authentication viable.
Supervisor: Qian Guo (EIT)
Examiner: Thomas Johansson (EIT)