Conceptual Approach to Detecting Deepfake Modifications of Biometric Images Using Neural Networks

The National Cybersecurity Cluster of Ukraine is functionally oriented towards building systems to protect various platforms of information infrastructure, including the creation of secure technologies for detecting deepfake modifications of biometric images based on neural networks in cyberspace. 

This space proposes a conceptual approach to detecting deepfake modifications, which is deployed based on the functioning of a convolutional neural network and the classifier algorithm for biometric images structured as “sensitivity-Yuden index-optimal threshold-specificity”.


The food industry is going through constant improvements and is subject to analyzing consumer needs, product quality research is essential to striking this balance. In this regard, meat quality, the most essential food category, should be studied with unbiased methods that give precise and correct results. Classification algorithms are considered one of the main components of developing an objective and reliable method of meat quality assessment.

Силуети кольору та яскравості зображень для їх класифікації та пошуку

Для зменшення часових затрат пошуку зображень у базах даних великих розмірів запропоновано підхід, що ґрунтується на визначенні силуетів яскравості зображень різних типів: фронтального та бічного для двох видів яскравості. Подальше приско- рення пошуку відбувається за рахунок заміни кривих силуетів поліноміальними функціями чебишовського типу. Додатковою ознакою є відстань до піків силуетів. Як приклади практичних даних використано зображення із відомих баз образів. Критеріями прийняті силуети та відстані до них.

On the publicly dangerous content of military administrative offenses

Abstract. Consideration of the provisions related to administrative illegality aimed at encroachment on social relations involves the analysis of its main components and causes of its occurrence in normal conditions of the functioning of society, as well as in special conditions to which the legal regime of martial law belongs. The complexity of the socio-economic and political situation in Ukraine led to the introduction of martial law by the President of Ukraine (February 2022) due to military aggression by the Russian Federation.

Tactical planning methods: meaning and typology in the system of circular business models of enterprises

Purpose. The concept of circular economy (closed-loop economy) emerged as an alternative economic model designed to reduce the negative impact on the environment, solve the problem of resource scarcity, extend the life cycle of products and solve global problems of the world economy and international economic relations on this basis. Obtaining the benefits of implementing circular business models, which consist in increasing the income of the world economy, saving resources, and increasing the number of jobs, requires reasonable and rational planning at enterprises.

PROMETHEE filter-based method for microarray gene expression data

Gene expression datasets have been successfully applied for a variety of purposes, including cancer classification.  The challenges faced in developing effective classifiers for expression datasets are high dimensionality and over-fitting.  Gene selection is an effective and efficient method to overcome these challenges and improve the predictive accuracy of a classifier.  Based on PROMETHEE, this paper introduces a multi-filter ensemble approach by integrating the results of two potential filters namely MaC$\Psi$-filter and PCRWG-filter to pre-select the most informati

Methods and means of determining objects of radio intelligence using the ontological approach

The article is devoted to the study of methods and means of determining objects of radio technical intelligence using machine learning technologies and an ontological approach. A naіve Bayesian classifier was used to identify objects of radio technical intelligence. The Naive Bayes classifier is a machine learning algorithm used to classify objects based on probabilities. In this article, a naive Bayesian classifier is used to determine the classes to which objects of radio technical intelligence belong.

Research into machine learning algorithms for the construction of mathematical models of multimodal data classification problems

Currently, machine learning algorithms (ML) are increasingly integrated into everyday life. There are many areas of modern life where classification methods are already used. Methods taking into account previous predictions and errors that are calculated as a result of data integration to obtain forecasts for obtaining the classification result are investigated. A general overview of classification methods is conducted. Experiments on machine learning algorithms for multimodal data are performed.


Purpose. The purpose of the research is to conduct a systematic study of existing classifications of measures of non-tariff regulation of foreign economic activity and analysis of the dynamics of the use of specific methods of non-tariff regulation in Ukraine and the world.

Density based fuzzy support vector machine: application to diabetes dataset

In this work, we propose a deep prediction diabetes system based on a new version of the support vector machine optimization model.  First, we determine three types of patients (noisy, cord, and interior) basing on specific parameters. Second, we equilibrate the clinical data sets by suppressing noisy and cord patients.  Third, we determine the support vectors by solving an optimization program with a reasonable size.