Multi-biometric liveness detection – A new perspective

Abstract

The problem of securing valuable data stored in databases has been of great  concern to organizations and individuals alike. The more worrisome is the increasing complexity of fraud perpetration by cyber criminals which demands that a more secure method be deployed. Basic Multi-biometric Authentication System was thought to have sealed the vulnerabilities and escape route from cyber criminals, but emerging attack patterns have proved us wrong. In spite of their benefits, multi-biometric systems also have peculiar challenges especially circumvention of security strategy, that is, how susceptible the system or the presented biometric modality is to spoof attacks and identity fraud. Liveness detection has been applied as an anti-spoofing mechanism to checkmate circumvention, however its application approach has thrown up more vulnerabilities. In this paper, we introduce our work and adopt the Structured Systems Analysis and Design Methodology (SSADM) to assist us understand the weaknesses and propose a solution which integrates liveness detection to halt spoofing of legitimate subjects, and propose a different approach for performing liveness detection in multi-biometric systems that  significantly minimizes the probability of circumvention and strengthens the overall security strategy of the authentication process. The expected output of the research is a prototype software for multi-modal biometrics that detects, in a randomized sequence, the absence of liveness and blocks access to critical infrastructure by fraudsters.

Keywords: Authentication, biometrics, liveness detection, spoofing, trait.