Slava Voloshynovskiy

Prof. Dr. Slava Voloshynovskiy

Stochastic Information Processing Group, Department of Computer Science, Faculty of Science, University of Geneva, Geneva, Switzerland

Research Focus & Metrics

Academic Career Length

27Years (2000-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 March 2023 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
BRBehrooz Razeghi
Behrooz Razeghi
FCFlavio Du Pin Calmon
Flavio Du Pin Calmon
DGDeniz Gunduz
Deniz Gunduz
Slava VoloshynovskiySlava Voloshynovskiy
Slava Voloshynovskiy
Bottleneck problems are an important class of optimization problems that have recently gained increasing attention in the domain of machine learning and information theory. They are widely used in generative models, fair machine learning algorithms, design of privacy-assuring mechanisms, and appear as information-theoretic performance bounds in various multi-user communication problems. In this work, we propose a general family of optimization problems, termed as complexity-leakage-utility bottleneck (CLUB) model, which (i) provides a unified theoretical framework that generalizes most of the state-of-the-art literature for the information-theoretic privacy models, (ii) establishes a new interpretation of the popular generative and discriminative models, (iii) constructs new insights for the generative compression models, and (iv) can be used to obtain fair generative models. We first formulate the CLUB model as a complexity-constrained privacy-utility optimization problem. We then connect it with the closely related bottleneck problems, namely information bottleneck (IB), privacy funnel (PF), deterministic IB (DIB), conditional entropy bottleneck (CEB), and conditional PF (CPF). We show that the CLUB model generalizes all these problems as well as most other information-theoretic privacy models. Then, we construct the deep variational CLUB (DVCLUB) models by employing neural networks to parameterize variational approximations of the associated information quantities. Building upon these information quantities, we present unified objectives of the supervised and unsupervised DVCLUB models. Leveraging the DVCLUB model in an unsupervised setup, we then connect it with state-of-the-art generative models, such as variational auto-encoders (VAEs), generative adversarial networks (GANs), as well as the Wasserstein GAN (WGAN), Wasserstein auto-encoder (WAE), and adversarial auto-encoder (AAE) models through the optimal transport (OT) problem. We then show that the DVCLUB model can also be used in fair representation learning problems, where the goal is to mitigate the undesired bias during the training phase of a machine learning model. We conduct extensive quantitative experiments on colored-MNIST and CelebA datasets.

27 August 2020 in Entropy
Verified
Journal Article
Open access
PDF file
Slava VoloshynovskiySlava Voloshynovskiy
Slava Voloshynovskiy
Olga TaranOlga Taran
Olga Taran
MKMouad Kondah
Mouad Kondah
THTaras Holotyak
Taras Holotyak
DRDanilo Rezende
Danilo Rezende
In this paper, we consider an information bottleneck (IB) framework for semi-supervised classification with several families of priors on latent space representation. We apply a variational decomposition of mutual information terms of IB. Using this decomposition we perform an analysis of several regularizers and practically demonstrate an impact of different components of variational model on the classification accuracy. We propose a new formulation of semi-supervised IB with hand crafted and learnable priors and link it to the previous methods such as semi-supervised versions of VAE (M1 + M2), AAE, CatGAN, etc. We show that the resulting model allows better understand the role of various previously proposed regularizers in semi-supervised classification task in the light of IB framework. The proposed IB semi-supervised model with hand-crafted and learnable priors is experimentally validated on MNIST under different amount of labeled data.

12 March 2024 in Astronomy & Astrophysics
Verified
Journal Article
Open access
MDM. Drozdova
M. Drozdova
VKVitaliy Kinakh
Vitaliy Kinakh
OBO. Bait
O. Bait
Olga TaranOlga Taran
Olga Taran
ELE. Lastufka
E. Lastufka
Slava VoloshynovskiySlava Voloshynovskiy
Slava Voloshynovskiy
Context.Reconstructing sky models from dirty radio images for accurate source extraction, including source localization and flux estimation, is a complex yet critical task, and has important applications in galaxy evolution studies at high redshift, particularly in deep extragalactic fields using for example the Atacama Large Millimetre Array (ALMA). With the development of large-scale projects, such as the Square Kilometre Array (SKA), we anticipate the need for more advanced source-extraction methods. Existing techniques, such as CLEAN and PyBDSF, currently struggle to effectively extract faint sources, highlighting the necessity for the development of more precise and robust methods.Aims.The success of the source-extraction process critically depends on the quality and accuracy of image reconstruction. As the imaging process represents an “information-lossy” operator, the reconstruction is characterized by uncertainty. The current study proposes the application of stochastic neural networks for the direct reconstruction of sky models from “dirty” images. This approach allows us to localize radio sources and to determine their fluxes with corresponding uncertainties, providing a potential advancement in the field of radio-source characterization.Methods.We used a dataset of 10 164 images simulated with the CASA tool based on the ALMA Cycle 5.3 antenna configuration. We applied conditional denoising diffusion probabilistic models (DDPMs) to directly reconstruct sky models from these dirty images, and then processed these models using Photutils to extract the coordinates and fluxes of the sources. To test the robustness of the proposed model, which was trained on a fixed water vapor value, we examined its performance under varying levels of water vapor.Results.We demonstrate that the proposed approach is state of the art in terms of source localisation, achieving over 90% completeness at a signal-to-noise ratio (S/N) of as low as 2. Additionally, the described method offers an inherent measure of prediction reliability thanks to the stochastic nature of the chosen model. In terms of flux estimation, the proposed model surpasses PyBDSF in terms of performance, accurately extracting fluxes for 96% of the sources in the test set, a notable improvement over the 57% achieved by CLEAN+ PyBDSF.Conclusions.Conditional DDPMs are a powerful tool for image-to-image translation, yielding accurate and robust characterization of radio sources, and outperforming existing methodologies. While this study underscores the significant potential of DDPMs for applications in radio astronomy, we also acknowledge certain limitations that accompany their use, and suggest directions for further refinement and research.

6 January 2024 in Journal of Biomedical Informatics
Verified
Journal Article
Closed access
ISIsaac Shiri
Isaac Shiri
BRBehrooz Razeghi
Behrooz Razeghi
SFSohrab Ferdowsi
Sohrab Ferdowsi
YSYazdan Salimi
Yazdan Salimi
DGDeniz Gündüz
Deniz Gündüz
Habib ZaidiHabib Zaidi
Habib Zaidi

1 June 2020 in EURASIP Journal on Information Security
Verified
Journal Article
Open access
PDF file
Olga TaranOlga Taran
Olga Taran
SRShideh Rezaeifar
Shideh Rezaeifar
THTaras Holotyak
Taras Holotyak
Slava VoloshynovskiySlava Voloshynovskiy
Slava Voloshynovskiy
In recent years, classification techniques based on deep neural networks (DNN) were widely used in many fields such as computer vision, natural language processing, and self-driving cars. However, the vulnerability of the DNN-based classification systems to adversarial attacks questions their usage in many critical applications. Therefore, the development of robust DNN-based classifiers is a critical point for the future deployment of these methods. Not less important issue is understanding of the mechanisms behind this vulnerability. Additionally, it is not completely clear how to link machine learning with cryptography to create an information advantage of the defender over the attacker. In this paper, we propose a key-based diversified aggregation (KDA) mechanism as a defense strategy in a gray- and black-box scenario. KDA assumes that the attacker (i) knows the architecture of classifier and the used defense strategy, (ii) has an access to the training data set, but (iii) does not know a secret key and does not have access to the internal states of the system. The robustness of the system is achieved by a specially designed key-based randomization. The proposed randomization prevents the gradients’ back propagation and restricts the attacker to create a “bypass” system. The randomization is performed simultaneously in several channels. Each channel introduces its own randomization in a special transform domain. The sharing of a secret key between the training and test stages creates an information advantage to the defender. Finally, the aggregation of soft outputs from each channel stabilizes the results and increases the reliability of the final score. The performed experimental evaluation demonstrates a high robustness and universality of the KDA against state-of-the-art gradient-based gray-box transferability attacks and the non-gradient-based black-box attacks (The results reported in this paper have been partially presented in CVPR 2019 (Taran et al., Defending against adversarial attacks by randomized diversification, 2019) & ICIP 2019 (Taran et al., Robustification of deep net classifiers by key-based diversified aggregation with pre-filtering, 2019)).

20 June 2023 in Astronomy & Astrophysics
Verified
Journal Article
Open access
PDF file
Olga TaranOlga Taran
Olga Taran
OBO. Bait
O. Bait
MDM. Dessauges-Zavadsky
M. Dessauges-Zavadsky
THT. Holotyak
T. Holotyak
DSD. Schaerer
D. Schaerer
Slava VoloshynovskiySlava Voloshynovskiy
Slava Voloshynovskiy
Context. Rising interest in radio astronomy and upcoming projects in the field is expected to produce petabytes of data per day, questioning the applicability of traditional radio astronomy data analysis approaches under the new large-scale conditions. This requires new, intelligent, fast, and efficient methods that potentially involve less input from the domain expert. Aims. In our work, we examine, for the first time, the possibility of fast and efficient source localization directly from the uv-observations, omitting the recovering of the dirty or clean images. Methods. We propose a deep neural network-based framework that takes as its input a low-dimensional vector of sampled uv-data and outputs source positions on the sky. We investigated a representation of the complex-valued input uv-data via the real and imaginary and the magnitude and phase components. We provided a comparison of the efficiency of the proposed framework with the traditional source localization pipeline based on the state-of-the-art Python Blob Detection and Source Finder (PyBDSF) method. The investigation was performed on a data set of 9164 sky models simulated using the Common Astronomy Software Applications (CASA) tool for the Atacama Large Millimeter Array (ALMA) Cycle 5.3 antenna configuration. Results. We investigated two scenarios: (i) noise-free as an ideal case and (ii) sky simulations including noise representative of typical extra-galactic millimeter observations. In the noise-free case, the proposed localization framework demonstrates the same high performance as the state-of-the-art PyBDSF method. For noisy data, however, our new method demonstrates significantly better performance, achieving a completeness level that is three times higher for sources with uniform signal-to-noise ratios (S/N) between 1 and 10, and a high increase in completeness in the low S/N regime. Furthermore, the execution time of the proposed framework is significantly reduced (by factors ~30) as compared to traditional methods that include image reconstructions from the uv-plane and subsequent source detections. Conclusions. The proposed framework for obtaining fast and efficient source localization directly from uv-plane observations shows very encouraging results, which could open new horizons for interferometric imaging with existing and future facilities.