Challenges and opportunities in biometric security: A survey. Issue 1 (2nd January 2022)

• Record Type: Journal Article
• Authors: Arora, Shefali; Bhatia, M.P.S
• Is Part Of: Information security journal. Volume 31:Issue 1(2022)
• Page Start: 28
• Page End: 48
• Publication Date: 2022-01-02
• Subjects: biometrics -- security -- privacy -- deep Learning -- convolutional Neural Networks -- spoofing; Computer security -- Periodicals; Electronic data processing departments -- Security measures -- Periodicals; 005.805
• DOI: 10.1080/19393555.2021.1873464
• Languages: English
• ISSNs: 1939-3555

Abstract

ABSTRACT: Biometric systems identify individuals based on unique traits such as the face, fingerprints, iris etc. The main objective of the study is to understand the role of deep learning in the process of authentication as well as its application in the enhancement of security of biometric systems. We highlight the studies using deep learning approaches to authenticate enrolled users under ideal and non-ideal environmental conditions. We summarize these approaches and explore the challenges that continue to restrict the full potential of biometric systems. The foremost are: building robust algorithms for authentication, ensuring the security of enrolled templates and protecting systems against spoofing attacks. In this paper, we review the performance achieved by various studies in overcoming the aforesaid challenges, along with the potential improvements and future directions in this domain.