Journal
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
Volume 15, Issue 7, Pages 4244-4253Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2019.2900665
Keywords
Artificial intelligence (AI); binary decision diagram (BDD); biometric template protection; edge biometrics; edge computing; finger vein; machine/deep learning
Ask authors/readers for more resources
With built-in artificial intelligence (AI), edge devices, e. g., smart cameras, can perform tasks like detecting and tracking individuals, which is referred to as edge biometrics. As a driving force for AI, machine/deep learning plays a critical role in edge biometrics. Machine/deep learning based edge biometric systems outperform their nonmachine learning counterpart. However, research shows that artificial neural networks, e. g., convolutional neural networks, are invertible such that adversaries can obtain a certain amount of information about the original inputs/ templates. This information leakage is not tolerable for biometric systems because biometric data in the original (raw) templates cannot be reset or replaced. Once compromised, they are lost forever. Therefore, how to prevent original biometric templates from being attacked through inverting deep neural networks is a pressing, but unsolved issue, for deep learning based biometric recognition. To address the issue, in this paper, we develop a novel biometric template protection algorithm using the binary decision diagram (BDD) for deep learning based finger-vein biometric systems. The proposed algorithm is capable of creating a new noninvertible version of the original finger-vein template, which is stacked with an artificial neural networkthe multilayer extreme learning machine (ML-ELM) to generate a privacy-preserving finger-vein recognition system, named BDD-ML-ELM. The proposed BDD-ML-ELM ensures the safety of the original finger-vein template even if its transformed version is compromised. The transformed template, if compromised, can be revoked and replaced with another new version by simply changing the user-specific keys. Therefore, the BDD-ML-ELM has a clear advantage over the existing machine/deep learning based biometric systems, whose raw biometric templates are vulnerable when the artificial neural network suffers an inversion attack.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available