S-BAN: Secure Biometric Authentication using Noise
Open Access
- 15 December 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Abstract
Biometric signal consisting of irrelevant or non-distinctive features can contain useful correlational properties that privacy-preserving verification schemes can exploit. While an efficient protocol for iris verification using noise has been presented [33], it is not applicable to other widely used modalities, i.e., face and fingerprint, since the methods of noise extraction and comparison are different. In this work, we design a verification protocol for secure dot product computation and also propose noise extraction mechanisms for face and fingerprint modalities. We evaluate the performance of the protocol on CFP, LFW, CelebA, FVC 2004 DB1A, DB2A, DB3A, and SOCOFing datasets. While the protocol exhibits a slight degradation in accuracy, it provides information-theoretic security with a practical computational complexity.Keywords
This publication has 23 references indexed in Scilit:
- Frontal to profile face verification in the wild2016
- Deep Learning Face Attributes in the Wild2015
- Privacy Protection in Biometric-Based Recognition Systems: A marriage between cryptography and signal processingIEEE Signal Processing Magazine, 2015
- FaceNet: A unified embedding for face recognition and clustering2015
- ABY - A Framework for Efficient Mixed-Protocol Secure Two-Party Computation2015
- A Fuzzy Vault SchemeDesigns, Codes and Cryptography, 2006
- Comparing passwords, tokens, and biometrics for user authenticationProceedings of the IEEE, 2003
- Similarity estimation techniques from rounding algorithms2002
- Efficient Multiparty Protocols Using Circuit Randomization2001
- Filterbank-based fingerprint matchingIEEE Transactions on Image Processing, 2000