Approximating Optimal Morphing Attacks using Template Inversion

Abstract

Recent works have demonstrated the feasibility of inverting face recognition systems, enabling to recover convincing face images using only their embeddings. We leverage such template inversion models to develop a novel type ofdeep morphing attack based on inverting a theoretical optimal morph embedding, which is obtained as an average of the face embeddings of source images. We experiment with two variants of this approach: the first one exploits a fully self-contained embedding-to-image inversion model, while the second leverages the synthesis network of a pretrained StyleGAN network for increased morph realism. We generate morphing attacks from several source datasets and study the effectiveness of those attacks against several face recognition networks. We showcase that our method can compete with and regularly beat the previous state of the art for deep-learning based morph generation in terms of effectiveness, both in white-box and black-box attack scenarios, and is additionally much faster to run. We hope this might facilitate the development of large scale deep morph datasets for training detection models.

arXiv commentPublished at the IEEE International Joint Conference on Biometrics (IJCB) 2023

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Denoising Diffusion Probabilistic Models
• On the Reconstruction of Face Images from Deep Face Templates
• Are GAN-based Morphs Threatening Face Recognition?
• Inverting face embeddings with convolutional neural networks
• Leveraging Diffusion For Strong and High Quality Face Morphing Attacks
• On the detection of morphing attacks generated by GANs
• MorphGANFormer: Transformer-based Face Morphing and De-Morphing
• Reconstruct Face from Features Using GAN Generator as a Distribution Constraint