In the recent years, the copy detection patterns (CDP) attracted a lot of attention as a link between the physical and digital worlds, which is of great interest for the internet of things and brand protection applications.
We present Turbo-Sim, a generalised autoencoder framework derived from principles of information theory that can be used as a generative model.
Normalizing flows are diffeomorphic, typically dimension-preserving, models trained using the likelihood of the model.
Nowadays, the modern economy critically requires reliable yet cheap protection solutions against product counterfeiting for the mass market.
We study the role of information complexity in privacy leakage about an attribute of an adversary's interest, which is not known a priori to the system designer.
In this paper, we propose a framework for privacy-preserving approximate near neighbor search via stochastic sparsifying encoding.
We propose a practical framework to address the problem of privacy-aware image sharing in large-scale setups.
In particular, we present a new interpretation of VAE family based on the IB framework using a direct decomposition of mutual information terms and show some interesting connections to existing methods such as VAE [2; 3], beta-VAE , AAE , InfoVAE  and VAE/GAN .
We investigate the privacy of two approaches to (biometric) template protection: Helper Data Systems and Sparse Ternary Coding with Ambiguization.
The robustness of the system is achieved by a specially designed key based randomization.
In this paper, we address the problem of data reconstruction from privacy-protected templates, based on recent concept of sparse ternary coding with ambiguization (STCA).
In recent years, printable graphical codes have attracted a lot of attention enabling a link between the physical and digital worlds, which is of great interest for the IoT and brand protection applications.
In this paper, we introduce a novel concept for learning of the parameters in a neural network.
We introduce a clustering principle that is based on evaluation of a parametric min-max measure for the discriminative prior.
We also introduce a criterion based on Kullback-Leibler divergence to reject doubtful examples.
The majority of the proposed existing adversarial attacks are based on the differentiability of the DNN cost function. Defence strategies are mostly based on machine learning and signal processing principles that either try to detect-reject or filter out the adversarial perturbations and completely neglect the classical cryptographic component in the defence.
A novel measure related to the discriminative prior is proposed and defined on the support intersection for the transform representations.
We present the multi-layer extension of the Sparse Ternary Codes (STC) for fast similarity search where we focus on the reconstruction of the database vectors from the ternary codes.
The sparsifying transform and privacy amplification are not symmetric for the data owner and data user.
A learning-based framework for representation of domain-specific images is proposed where joint compression and denoising can be done using a VQ-based multi-layer network.
Furthermore, we also propose a general-purpose pre-processing for natural images which makes them suitable for such quantization.
This paper addresses the problem of Approximate Nearest Neighbor (ANN) search in pattern recognition where feature vectors in a database are encoded as compact codes in order to speed-up the similarity search in large-scale databases.