Search Results for author: Slava Voloshynovskiy

Found 25 papers, 9 papers with code

Mobile authentication of copy detection patterns

no code implementations4 Mar 2022 Olga Taran, Joakim Tutt, Taras Holotyak, Roman Chaban, Slavi Bonev, Slava Voloshynovskiy

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.

Copy Detection

Turbo-Sim: a generalised generative model with a physical latent space

no code implementations20 Dec 2021 Guillaume Quétant, Mariia Drozdova, Vitaliy Kinakh, Tobias Golling, Slava Voloshynovskiy

We present Turbo-Sim, a generalised autoencoder framework derived from principles of information theory that can be used as a generative model.

Funnels: Exact maximum likelihood with dimensionality reduction

1 code implementation15 Dec 2021 Samuel Klein, John A. Raine, Sebastian Pina-Otey, Slava Voloshynovskiy, Tobias Golling

Normalizing flows are diffeomorphic, typically dimension-preserving, models trained using the likelihood of the model.

Dimensionality Reduction

Machine learning attack on copy detection patterns: are 1x1 patterns cloneable?

1 code implementation5 Oct 2021 Roman Chaban, Olga Taran, Joakim Tutt, Taras Holotyak, Slavi Bonev, Slava Voloshynovskiy

Nowadays, the modern economy critically requires reliable yet cheap protection solutions against product counterfeiting for the mass market.

Copy Detection

Variational Leakage: The Role of Information Complexity in Privacy Leakage

1 code implementation5 Jun 2021 Amir Ahooye Atashin, Behrooz Razeghi, Deniz Gündüz, Slava Voloshynovskiy

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.

Representation Learning

Privacy-Preserving Near Neighbor Search via Sparse Coding with Ambiguation

no code implementations8 Feb 2021 Behrooz Razeghi, Sohrab Ferdowsi, Dimche Kostadinov, Flavio. P. Calmon, Slava Voloshynovskiy

In this paper, we propose a framework for privacy-preserving approximate near neighbor search via stochastic sparsifying encoding.

Fairness

Privacy-Preserving Image Sharing via Sparsifying Layers on Convolutional Groups

1 code implementation4 Feb 2020 Sohrab Ferdowsi, Behrooz Razeghi, Taras Holotyak, Flavio P. Calmon, Slava Voloshynovskiy

We propose a practical framework to address the problem of privacy-aware image sharing in large-scale setups.

Information bottleneck through variational glasses

no code implementations2 Dec 2019 Slava Voloshynovskiy, Mouad Kondah, Shideh Rezaeifar, Olga Taran, Taras Holotyak, Danilo Jimenez Rezende

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 [11], AAE [12], InfoVAE [5] and VAE/GAN [13].

Single-Component Privacy Guarantees in Helper Data Systems and Sparse Coding with Ambiguation

no code implementations15 Jul 2019 Behrooz Razeghi, Taras Stanko, Boris Škorić, Slava Voloshynovskiy

We investigate the privacy of two approaches to (biometric) template protection: Helper Data Systems and Sparse Ternary Coding with Ambiguization.

Reconstruction of Privacy-Sensitive Data from Protected Templates

no code implementations8 May 2019 Shideh Rezaeifar, Behrooz Razeghi, Olga Taran, Taras Holotyak, Slava Voloshynovskiy

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).

Quantization

Defending against adversarial attacks by randomized diversification

1 code implementation CVPR 2019 Olga Taran, Shideh Rezaeifar, Taras Holotyak, Slava Voloshynovskiy

The vulnerability of machine learning systems to adversarial attacks questions their usage in many applications.

Clonability of anti-counterfeiting printable graphical codes: a machine learning approach

1 code implementation18 Mar 2019 Olga Taran, Slavi Bonev, Slava Voloshynovskiy

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.

Bridging machine learning and cryptography in defence against adversarial attacks

3 code implementations5 Sep 2018 Olga Taran, Shideh Rezaeifar, Slava Voloshynovskiy

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.

Network Learning with Local Propagation

no code implementations20 May 2018 Dimche Kostadinov, Behrooz Razeghi, Sohrab Ferdowsi, Slava Voloshynovskiy

This paper presents a locally decoupled network parameter learning with local propagation.

Learning non-linear transform with discriminative and minimum information loss priors

no code implementations ICLR 2018 Dimche Kostadinov, Slava Voloshynovskiy

A novel measure related to the discriminative prior is proposed and defined on the support intersection for the transform representations.

A multi-layer network based on Sparse Ternary Codes for universal vector compression

no code implementations31 Oct 2017 Sohrab Ferdowsi, Slava Voloshynovskiy, Dimche Kostadinov

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.

Privacy Preserving Identification Using Sparse Approximation with Ambiguization

no code implementations29 Sep 2017 Behrooz Razeghi, Slava Voloshynovskiy, Dimche Kostadinov, Olga Taran

The sparsifying transform and privacy amplification are not symmetric for the data owner and data user.

A multi-layer image representation using Regularized Residual Quantization: application to compression and denoising

no code implementations7 Jul 2017 Sohrab Ferdowsi, Slava Voloshynovskiy, Dimche Kostadinov

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.

Denoising Quantization

Regularized Residual Quantization: a multi-layer sparse dictionary learning approach

no code implementations1 May 2017 Sohrab Ferdowsi, Slava Voloshynovskiy, Dimche Kostadinov

Furthermore, we also propose a general-purpose pre-processing for natural images which makes them suitable for such quantization.

Dictionary Learning Quantization +1

Sparse Ternary Codes for similarity search have higher coding gain than dense binary codes

no code implementations26 Jan 2017 Sohrab Ferdowsi, Slava Voloshynovskiy, Dimche Kostadinov, Taras Holotyak

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.

Binarization

Cannot find the paper you are looking for? You can Submit a new open access paper.