Slava Voloshynovskiy

research

∙ 06/23/2022

Authentication of Copy Detection Patterns under Machine Learning Attacks: A Supervised Approach

Copy detection patterns (CDP) are an attractive technology that allows m...

Brian Pulfer, et al. ∙

research

∙ 03/04/2022

Mobile authentication of copy detection patterns

In the recent years, the copy detection patterns (CDP) attracted a lot o...

Olga Taran, et al. ∙

research

∙ 12/15/2021

Funnels: Exact maximum likelihood with dimensionality reduction

Normalizing flows are diffeomorphic, typically dimension-preserving, mod...

Samuel Klein, et al. ∙

research

∙ 10/05/2021

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

Nowadays, the modern economy critically requires reliable yet cheap prot...

Roman Chaban, et al. ∙

research

∙ 10/05/2021

Mobile authentication of copy detection patterns: how critical is to know fakes?

Protection of physical objects against counterfeiting is an important ta...

Olga Taran, et al. ∙

research

∙ 06/05/2021

Variational Leakage: The Role of Information Complexity in Privacy Leakage

We study the role of information complexity in privacy leakage about an ...

Amir Ahooye Atashin, et al. ∙

research

∙ 02/08/2021

Privacy-Preserving Near Neighbor Search via Sparse Coding with Ambiguation

In this paper, we propose a framework for privacy-preserving approximate...

Behrooz Razeghi, et al. ∙

research

∙ 09/09/2020

On Perfect Obfuscation: Local Information Geometry Analysis

We consider the problem of privacy-preserving data release for a specifi...

Behrooz Razeghi, et al. ∙

research

∙ 02/04/2020

Privacy-Preserving Image Sharing via Sparsifying Layers on Convolutional Groups

We propose a practical framework to address the problem of privacy-aware...

Sohrab Ferdowsi, et al. ∙

research

∙ 12/02/2019

Information bottleneck through variational glasses

Information bottleneck (IB) principle [1] has become an important elemen...

Slava Voloshynovskiy, et al. ∙

research

∙ 09/13/2019

ρ-VAE: Autoregressive parametrization of the VAE encoder

We make a minimal, but very effective alteration to the VAE model. This ...

Sohrab Ferdowsi, et al. ∙

research

∙ 07/15/2019

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

We investigate the privacy of two approaches to (biometric) template pro...

Behrooz Razeghi, et al. ∙

research

∙ 05/14/2019

Robustification of deep net classifiers by key based diversified aggregation with pre-filtering

In this paper, we address a problem of machine learning system vulnerabi...

Olga Taran, et al. ∙

research

∙ 05/08/2019

Reconstruction of Privacy-Sensitive Data from Protected Templates

In this paper, we address the problem of data reconstruction from privac...

Shideh Rezaeifar, et al. ∙

research

∙ 04/01/2019

Defending against adversarial attacks by randomized diversification

The vulnerability of machine learning systems to adversarial attacks que...

Olga Taran, et al. ∙

research

∙ 03/18/2019

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

In recent years, printable graphical codes have attracted a lot of atten...

Olga Taran, et al. ∙

research

∙ 01/31/2019

Network Parameter Learning Using Nonlinear Transforms, Local Representation Goals and Local Propagation Constraints

In this paper, we introduce a novel concept for learning of the paramete...

Dimche Kostadinov, et al. ∙

research

∙ 01/30/2019

Clustering with Jointly Learned Nonlinear Transforms Over Discriminating Min-Max Similarity/Dissimilarity Assignment

This paper presents a novel clustering concept that is based on jointly ...

Dimche Kostadinov, et al. ∙

research

∙ 12/10/2018

Aggregation and Embedding for Group Membership Verification

This paper proposes a group membership verification protocol preventing ...

Marzieh Gheisari, et al. ∙

research

∙ 09/10/2018

Classification by Re-generation: Towards Classification Based on Variational Inference

As Deep Neural Networks (DNNs) are considered the state-of-the-art in ma...

Shideh Rezaeifar, et al. ∙

research

∙ 09/05/2018

Bridging machine learning and cryptography in defence against adversarial attacks

In the last decade, deep learning algorithms have become very popular th...

Olga Taran, et al. ∙

research

∙ 06/07/2018

Privacy-Preserving Identification via Layered Sparse Code Design: Distributed Servers and Multiple Access Authorization

We propose a new computationally efficient privacy-preserving identifica...

Behrooz Razeghi, et al. ∙

research

∙ 05/20/2018

Network Learning with Local Propagation

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

Dimche Kostadinov, et al. ∙

research

∙ 10/31/2017

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

We present the multi-layer extension of the Sparse Ternary Codes (STC) f...

Sohrab Ferdowsi, et al. ∙

research

∙ 09/29/2017

Privacy Preserving Identification Using Sparse Approximation with Ambiguization

In this paper, we consider a privacy preserving encoding framework for i...

Behrooz Razeghi, et al. ∙

research

∙ 07/07/2017

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

A learning-based framework for representation of domain-specific images ...

Sohrab Ferdowsi, et al. ∙

research

∙ 01/26/2017

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

This paper addresses the problem of Approximate Nearest Neighbor (ANN) s...

Sohrab Ferdowsi, et al. ∙

Slava Voloshynovskiy

Featured Co-authors

Deniz Gündüz

Flavio P. Calmon

Danilo Jimenez Rezende

Teddy Furon

Dimche Kostadinov

Laurent Amsaleg

Olga Taran

Behrooz Razeghi

Taras Holotyak

Sohrab Ferdowsi

Boris Skoric

Authentication of Copy Detection Patterns under Machine Learning Attacks: A Supervised Approach

Mobile authentication of copy detection patterns

Funnels: Exact maximum likelihood with dimensionality reduction

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

Mobile authentication of copy detection patterns: how critical is to know fakes?

Variational Leakage: The Role of Information Complexity in Privacy Leakage

Privacy-Preserving Near Neighbor Search via Sparse Coding with Ambiguation

On Perfect Obfuscation: Local Information Geometry Analysis

Privacy-Preserving Image Sharing via Sparsifying Layers on Convolutional Groups

Information bottleneck through variational glasses

ρ-VAE: Autoregressive parametrization of the VAE encoder

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

Robustification of deep net classifiers by key based diversified aggregation with pre-filtering

Reconstruction of Privacy-Sensitive Data from Protected Templates

Defending against adversarial attacks by randomized diversification

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

Network Parameter Learning Using Nonlinear Transforms, Local Representation Goals and Local Propagation Constraints

Clustering with Jointly Learned Nonlinear Transforms Over Discriminating Min-Max Similarity/Dissimilarity Assignment

Aggregation and Embedding for Group Membership Verification

Classification by Re-generation: Towards Classification Based on Variational Inference

Bridging machine learning and cryptography in defence against adversarial attacks

Privacy-Preserving Identification via Layered Sparse Code Design: Distributed Servers and Multiple Access Authorization

Network Learning with Local Propagation

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

Privacy Preserving Identification Using Sparse Approximation with Ambiguization

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

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