generator network
- North America > Canada > Quebec > Montreal (0.04)
- Europe > United Kingdom > England > Oxfordshire > Oxford (0.04)
- North America > United States > Massachusetts > Middlesex County > Cambridge (0.15)
- North America > Canada (0.04)
Face Reconstruction from Facial Templates by Learning Latent Space of a Generator Network
In this paper, we focus on the template inversion attack against face recognition systems and propose a new method to reconstruct face images from facial templates. Within a generative adversarial network (GAN)-based framework, we learn a mapping from facial templates to the intermediate latent space of a pre-trained face generation network, from which we can generate high-resolution realistic reconstructed face images. We show that our proposed method can be applied in whitebox and blackbox attacks against face recognition systems. Furthermore, we evaluate the transferability of our attack when the adversary uses the reconstructed face image to impersonate the underlying subject in an attack against another face recognition system. Considering the adversary's knowledge and the target face recognition system, we define five different attacks and evaluate the vulnerability of state-of-the-art face recognition systems. Our experiments show that our proposed method achieves high success attack rates in whitebox and blackbox scenarios. Furthermore, the reconstructed face images are transferable and can be used to enter target face recognition systems with a different feature extractor model. We also explore important areas in the reconstructed face images that can fool the target face recognition system.
Learning Probabilistic Models from Generator Latent Spaces with Hat EBM
This work proposes a method for using any generator network as the foundation of an Energy-Based Model (EBM). Our formulation posits that observed images are the sum of unobserved latent variables passed through the generator network and a residual random variable that spans the gap between the generator output and the image manifold. One can then define an EBM that includes the generator as part of its forward pass, which we call the Hat EBM. The model can be trained without inferring the latent variables of the observed data or calculating the generator Jacobian determinant. This enables explicit probabilistic modeling of the output distribution of any type of generator network. Experiments show strong performance of the proposed method on (1) unconditional ImageNet synthesis at 128$\times$128 resolution, (2) refining the output of existing generators, and (3) learning EBMs that incorporate non-probabilistic generators.
- North America > United States > Oregon > Benton County > Corvallis (0.04)
- North America > United States > California > Los Angeles County > Long Beach (0.04)
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
- North America > United States (0.14)
- Europe > Germany > Baden-Württemberg > Freiburg (0.04)
- North America > Canada > Quebec > Montreal (0.04)
- (2 more...)
- North America > Canada > Quebec > Montreal (0.04)
- Europe > United Kingdom > England > Oxfordshire > Oxford (0.04)