Secure Triplet Loss for End-to-End Deep Biometrics

• Type: Article in International Conference Proceedings Book
• Date: 2020

Authors

Joao Ribeiro Pinto (Author) Other; Jaime S. Cardoso (Author) FEUP; Miguel V. Correia (Author) FEUP

Conference proceedings International

Title: 8th International Workshop on Biometrics and Forensics, IWBF 2020, Porto, Portugal, April 29-30, 2020

Pages: 1-6

8th International Workshop on Biometrics and Forensics, IWBF 2020

29 April 2020 through 30 April 2020

Indexing

ISI Web of Knowledge - 1 Citation

ISI Web of Science

Scopus - 2 Citations

INSPEC

Other information

Authenticus ID: P-00S-6QV

DOI: 10.1109/iwbf49977.2020.9107958

Abstract (EN): Although deep learning is being widely adopted for every topic in pattern recognition, its use for secure and cancelable biometrics is currently reserved for feature extraction and biometric data preprocessing, limiting achievable performance. In this paper, we propose a novel formulation of the triplet loss methodology, designated as secure triplet loss, that enables biometric template cancelability with end-to-end convolutional neural networks, using easily changeable keys. Trained and evaluated for electrocardiogram-based biometrics, the network revealed easy to optimize using the modified triplet loss and achieved superior performance when compared with the state- of-the-art (10.63% equal error rate with data from 918 subjects of the UofTDB database). Additionally, it ensured biometric template security and effective template cancelability. Although further efforts are needed to avoid template linkability, the proposed secure triplet loss shows promise in template cancelability and non-invertibility for biometric recognition while taking advantage of the full power of convolutional neural networks. © 2020 IEEE.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 6