The Impact of Print-Scanning in Heterogeneous Morph Evaluation Scenarios
This addresses vulnerabilities in biometric security systems, particularly for applications like border control or identity verification, but is incremental as it focuses on a specific attack scenario.
The paper tackles the problem of face morphing attacks on face recognition systems by investigating how print-scanning affects detection in heterogeneous scenarios, finding that it can increase the Mated Morph Presentation Match Rate by up to 8.48% and raise the Morphing Attack Classification Error Rate by up to 96.12% when detection algorithms are not trained for such conditions.
Face morphing attacks pose an increasing threat to face recognition (FR) systems. A morphed photo contains biometric information from two different subjects to take advantage of vulnerabilities in FRs. These systems are particularly susceptible to attacks when the morphs are subjected to print-scanning to mask the artifacts generated during the morphing process. We investigate the impact of print-scanning on morphing attack detection through a series of evaluations on heterogeneous morphing attack scenarios. Our experiments show that we can increase the Mated Morph Presentation Match Rate (MMPMR) by up to 8.48%. Furthermore, when a Single-image Morphing Attack Detection (S-MAD) algorithm is not trained to detect print-scanned morphs the Morphing Attack Classification Error Rate (MACER) can increase by up to 96.12%, indicating significant vulnerability.