MIPGAN—Generating Strong and High Quality Morphing Attacks Using Identity Prior Driven GAN

Face morphing attacks target to circumvent Recognition Systems (FRS) by employing face images derived from multiple data subjects (e.g., accomplices and malicious actors). Morphed can be verified against contributing with a reasonable success rate, given they have high degree of facial resemblance. The is directly dependent on the quality generated morph images. We present new approach for generating strong extending our earlier framework morphs. using an Identity Prior Driven Generative Adversarial Network, which we refer as MIPGAN (Morphing through driven GAN). proposed StyleGAN newly formulated loss function exploiting perceptual identity factor generate morphed image minimal artefacts resolution. demonstrate approach's applicability evaluating its vulnerability both commercial deep learning based System rate attacks. Extensive experiments are carried out assess FRS's generation technique three types such digital images, re-digitized (printed scanned) compressed after re-digitization Morph Dataset. obtained results that poses threat FRS.