Robustness of Facial Recognition to GAN-based Face-morphing Attacks
This research addresses the critical problem of the vulnerability of facial recognition systems to sophisticated face-morphing attacks for security and identity verification applications.
This paper investigates the robustness of facial recognition (FR) algorithms against two novel GAN-based face-morphing attack methods. It demonstrates that while FR fidelity improvements reduce attack success rates, this is contingent on considering morphed images when establishing operational acceptance thresholds.
Face-morphing attacks have been a cause for concern for a number of years. Striving to remain one step ahead of attackers, researchers have proposed many methods of both creating and detecting morphed images. These detection methods, however, have generally proven to be inadequate. In this work we identify two new, GAN-based methods that an attacker may already have in his arsenal. Each method is evaluated against state-of-the-art facial recognition (FR) algorithms and we demonstrate that improvements to the fidelity of FR algorithms do lead to a reduction in the success rate of attacks provided morphed images are considered when setting operational acceptance thresholds.