Neural Network to Forge Fingerprints

DeepMasterPrints can be used as a key for hacking biometric identification systems
16 November 2018   677

Researchers at New York University have developed a generative-adversary network for prototyping fingerprints. Images of these prints, called DeepMasterPrints, can be used as a key for hacking biometric identification systems.

The principle of creating DeepMasterPrints is to use two properties of fingerprints and biometric systems.

Many scanners do not read the entire print. They process a part of it, and then compare it with the exact same part of the print from the database. Thus, a fake print should correspond only to a part of the original one.

Secondly, the researchers noted that some features of prints are repeated. This means that an artificial footprint that contains a set of common features will correspond to several genuine footprints at once.

DeepMasterPrints
DeepMasterPrints

The study showed that at a system tolerance level of 0.1%, artificial fingerprints can forge up to 23% of all fingerprints from the database. An error of 1% allows neural networks to fake up to 77% of prints.

Experts compare the use of DeepMasterPrints with a brute-force attack, when an attacker sorts through all the passwords that may be appropriate in this case.

Nvidia to Open SPADE Source Code

SPADE machine learning system creates realistic landscapes based on rough human sketches
15 April 2019   656

NVIDIA has released the source code for the SPADE machine learning system (GauGAN), which allows for the synthesis of realistic landscapes based on rough sketches, as well as training models associated with the project. The system was demonstrated in March at the GTC 2019 conference, but the code was published only yesterday. The developments are open under the non-free license CC BY-NC-SA 4.0 (Creative Commons Attribution-NonCommercial-ShareAlike 4.0), allowing use only for non-commercial purposes. The code is written in Python using the PyTorch framework.

Sketches are drawn up in the form of a segmented map that determines the placement of exemplary objects on the scene. The nature of the generated objects is set using color labels. For example, a blue fill turns into sky, blue into water, dark green into trees, light green into grass, light brown into stones, dark brown into mountains, gray into snow, a brown line into a road, and a blue line into the river. Additionally, based on the choice of reference images, the overall style of the composition and the time of day are determined. The proposed tool for creating virtual worlds can be useful to a wide range of specialists, from architects and urban planners to game developers and landscape designers.

Objects are synthesized by a generative-adversarial neural network (GAN), which, based on a schematic segmented map, creates realistic images by borrowing parts from a model previously trained on several million photographs. In contrast to the previously developed systems of image synthesis, the proposed method is based on the use of adaptive spatial transformation followed by transformation based on machine learning. Processing a segmented map instead of semantic markup allows you to achieve an exact match of the result and control the style.

To achieve realism, two competing neural networks are used: the generator and the discriminator (Discriminator). The generator generates images based on mixing elements of real photos, and the discriminator identifies possible deviations from real images. As a result, a feedback is formed, on the basis of which the generator begins to assemble more and more qualitative samples, until the discriminator ceases to distinguish them from the real ones.