Vladyslav Shkolnikov

Vladyslav Shkolnikov

Auto-generated profile, based on publicly available information

Vladyslav Shkolnikov

National Academy of Internal Affairs

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
3 July 2025 in Management (Montevideo)
Verified
Journal Article
Open access
PDF file
KOKostiantyn Orobets
Kostiantyn Orobets
VSVladyslav Shkolnikov
Vladyslav Shkolnikov
TBTetiana Batrachenko
Tetiana Batrachenko
TBTetiana Baranovska
Tetiana Baranovska
VSValeriy Sereda
Valeriy Sereda
Introduction: The legal regime of cryptocurrency in different countries of the world is heterogeneous. In some, it is not defined at all, which leads to legal conflicts, including when qualifying crimes committed with cryptocurrency use. The situation is further complicated because such crimes can occur in the territories of several states where cryptocurrency has a different legal regime. Traditional legislation and mechanisms for combating money laundering and terrorist financing are practically ineffective in the landscape of crimes involving the use of cryptocurrency.Objectives: The aim of the study is to systematise the main patterns of crimes related to the use of cryptocurrency, as well as analyse existing vectors of their legal assessment, appropriate design and application of effective methods of combating these crimes.Methods: Based on the methods of analysis and synthesis, qualitative data analysis, using content analysis as the primary research tool, it is shown that the main problem in preventing the use of cryptocurrency in predicate crimes lies in the technical difficulty of identifying a person or group of persons who carry out cryptocurrency transactions for illegal purposes. Such goals may be aimed at legalising funds, i.e., concealing their illegal origin, making payments in a hidden network, organising various fraudulent schemes, financing terrorism, and other crimes.Results: The article argues that given the technical specifics of cryptocurrency transactions and the technical capabilities of "masking" the origin of cryptocurrency funds, it is necessary to develop methods for studying trace formation and develop an algorithm for establishing and consolidating forensically significant information for this type of crime. The results indicate that the future of law enforcement in the fight against cryptocurrency-related crime will require a multifaceted approach. Agencies must adopt a proactive approach by foreseeing emerging criminal strategies. To protect the public from crimes using digital assets, law enforcement must be flexible, progressive, and technologically savvy as cryptocurrencies continue to develop. The development of provisions on cryptocurrency also determines the theoretical significance of the work as an object and means of committing crimes, a surrogate means of payment during the commission of certain crimes.Conclusions: The practical significance of the work lies in the possibility of using its results to solve problems arising in the law-making activities of state authorities and law enforcement activities, as well as in developing recommendations for improving criminal legislation in the field of cryptocurrency-related crimes.

28 March 2025 in Uzhhorod National University Herald. Series: Law
Verified
Journal Article
Open access
PDF file
VSV. I. Shkolnikov
V. I. Shkolnikov
Modern information technologies allow law enforcement agencies to significantly increase the efficiency of pre-trial investigations of criminal offenses. The use of virtual assets by offenders in the course of committing illegal activities necessitates the use of technologies for processing and analysing the flow of virtual assets by law enforcement agencies during pre-trial investigations. The purpose of this article is to research the problem of obtaining information about flow of virtual assets and the application of appropriate technologies for the processing and analysis of such kind of information by law enforcement agencies. The basis of the methodological toolkit was general scientific and special methods of cognition, including comparative, synthetic, logico-semantic, normative-dogmatic (formal-legal), legal regulation, thanks to which it was possible to consider the peculiarities of the application by law enforcement agencies of Ukraine of technologies for processing and analysing flow of virtual assets. The reasons and ways of solving the problem of processing and analysing flow of virtual assets have been determined: information provided in an unstructured form; information provided in large volumes; a large number of tabs with information relevant to the pre-trial investigation (applies to formats for Microsoft Excel files); additional processing is required to isolate bank account details; transactions that were carried out between users of the virtual asset exchange service require additional processing in order to obtain a single structure of all transactions; there is a need to convert virtual assets into the hryvnia equivalent at the exchange rate on the day of the transaction etc. The author’s specialized computer program «Bankir-v.2.0» is considered, which implements the functionality of automating the processes of processing and analysing flow of virtual assets. It has been determined that the purpose of analysing the movement of virtual assets may be to establish: identification data of individuals associated with a registered account on a virtual asset exchange service; features of the financial and economic activities of certain individuals and legal entities; involvement of a person in the sale of objects or substances prohibited for civil circulation; undeclared income of a civil servant; facts of legalization (laundering) of proceeds from crime etc. The practical value of scientific results lies in the fact that they can be used to determine ways of obtaining, processing and analysing information about flow of virtual assets.

1 June 2026 in PROBLEMS IN PROGRAMMING
Verified
Journal Article
Closed access
VHV.G. Huskova
V.G. Huskova
VSV.I. Shkolnikov
V.I. Shkolnikov
BLB.S. Lysov
B.S. Lysov
AKA.A. Khalygov
A.A. Khalygov
The article addresses the problem of generating recommendations for critical infrastructure objects under conditions of increasing cyber threats, large volumes of streaming data, and the need for rapid decision-making. The relevance of the study is determined by the necessity to enhance the resilience of critical infrastructure through the use of intelligent decision support systems. The purpose of the research is to develop an integrated approach to recommendation generation based on streaming data, machine learning methods, Bayesian ranking, and explainable artificial intelligence. The study employs methods of anomaly detection, threat classification, risk forecasting, rule-based filtering, and XAI approaches for explaining generated recommendations. The proposed architecture provides real-time data processing and takes into account risks, security policies, and the operational context of the infrastructure object. Experimental validation on datasets demonstrated high system efficiency: F1 = 0.90, AUROC = 0.96, while processing latency did not exceed 0.8 s under a load of up to 10,000 messages per second. It was established that the adaptive self-updating mechanism reduces the number of false alarms by 43% and increases operators’ trust in the recommendation system. The obtained results confirm the prospects for the practical application of the proposed approach in supporting decision-making processes at critical infrastructure facilities.

29 September 2026 in Вісник Східноукраїнського національного університету імені Володимира Даля
Verified
Journal Article
Open access
PDF file
ВГВ.г. Гуськова
В.г. Гуськова
ВШВ.і. Школьников
В.і. Школьников
Системи критичної інфраструктури функціонують в умовах високої динамічності, нестаціонарності та невизначеності, що висуває підвищені вимоги до сучасних систем підтримки прийняття рішень. Забезпечення своєчасного та достовірного прогнозування стану таких об'єктів є важливою умовою підвищення їхньої надійності та безпеки функціонування. Існуючі методи прогнозування забезпечують високу точність, проте недостатньо враховують невизначеність прогнозів, обмежено підтримують інтерпретованість результатів і недостатньо адаптуються до зміни умов експлуатації, а прогнозування, оцінювання невизначеності та пояснюваність здебільшого реалізуються ізольовано. Метою роботи є підвищення надійності, адаптивності та інтерпретованості підтримки прийняття рішень шляхом розроблення інтегрованої системи прогнозування стану об'єктів критичної інфраструктури. Запропоновано модульну архітектуру системи, що об'єднує модулі збору та попередньої обробки даних, формування ознак, ансамблевого прогнозування, оцінювання невизначеності, пояснюваності та підтримки прийняття рішень. Гібридний ансамбль поєднує статистичні моделі, регресори машинного навчання та рекурентні нейронні мережі з динамічним байєсівським зважуванням прогнозів. Наукова новизна полягає в інтеграції гібридного прогнозування, динамічної байєсівської агрегації моделей, оцінювання невизначеності прогнозів і адаптивного навчання із замкненим контуром зворотного зв'язку в межах єдиної інформаційної технології підтримки прийняття рішень. Експериментальну перевірку виконано на відкритому наборі даних ETTh1 (17 420 спостережень, 41 ознака) за протоколом ковзного початку (20 вікон оцінювання, горизонти 1–24 год). Запропонована система забезпечила MAE = 1,329 ± 0,448, RMSE = 1,911 та R² = 0,897, що відповідає зменшенню похибки на 24,6–30,1 % порівняно з окремими моделями машинного навчання. Абляційне дослідження показало, що модуль адаптивного навчання забезпечує зменшення MAE на 82,4 %, а модуль байєсівської агрегації — коректне калібрування прогнозних інтервалів (PICP = 0,952 за номінального рівня 0,95). Індекс довіри значуще корелює з фактичною похибкою, що дає змогу використовувати його як критерій ескалації рішення до експерта. Статистичну значущість відмінностей підтверджено критеріями Вілкоксона та Фрідмана.

25 June 2026 in Cybersecurity: Education, Science, Technique
Verified
Journal Article
Open access
PDF file
VSVladyslav Shkolnikov
Vladyslav Shkolnikov
BOBohdan
Bohdan
AKArtem Khalygov
Artem Khalygov
VHVira Huskova
Vira Huskova
The article investigates the problem of integrating neural network-based anomaly detection methods with formalized risk assessment mechanisms and decision support models within critical infrastructure environments. The introduction substantiates the relevance of ensuring cyber resilience of critical infrastructure under conditions of increasing attack complexity, expanding attack surfaces, and the limitations of traditional security systems. The problem statement identifies key limitations of existing neural network approaches, including the lack of contextualization, risk-oriented interpretation, and automated recommendation generation mechanisms. The literature review systematizes contemporary approaches to LSTM-, autoencoder-, and transformer-based anomaly detection, as well as methods for dynamic cyber risk assessment. The research objective is formulated as the development of a hybrid architecture that integrates behavioral anomaly detection, aggregation of anomaly scores into an integral risk indicator, and automated response scenario generation. The proposed multi-layer architecture includes a Data Layer, Neural Detection Layer (LSTM Autoencoder), Risk Aggregation Layer (top-k aggregation with asset criticality coefficient), and a Decision Support Layer with a threshold-based recommendation model. The computation of anomaly scores, integral risk, and management action functions is formally defined. Experimental validation was conducted on the BETH dataset using two evaluation modes: Normal-only and Mixed. In the Mixed mode, the model achieved ROC-AUC = 0.874 and PR-AUC = 0.828 at the window level, and Session ROC-AUC = 0.8235 after risk aggregation. The Action Precision metric of 0.9333 confirms the effectiveness of the incident prioritization mechanism. Low latency (~0.35 ms) demonstrates suitability for near real-time application. The conclusions demonstrate that integrating a neural anomaly detector with a risk-oriented decision support model improves interpretability, reduces false escalations, and ensures adaptability to different data regimes.

29 October 2026 in Eastern-European Journal of Enterprise Technologies
Verified
Journal Article
Open access
PDF file
VHVira Huskova
Vira Huskova
VSVladyslav Shkolnikov
Vladyslav Shkolnikov
AKArtem Khalyhov
Artem Khalyhov
BLBohdan Lysov
Bohdan Lysov
This work investigates the process of assessing the cyber risk to a corporate information system based on the behavior of its users and related information entities. One of the most difficult tasks in ensuring the cybersecurity of corporate information systems is the timely detection of internal threats associated with the actions of legitimate users. This issue relates to the fact that existing behavioral analytics tools are mostly limited to detecting anomalies, process groups of features in isolation, and do not provide an integrated quantitative assessment of risk, which generates many false positives. To resolve the issue, a hybrid behavioral profiling framework has been proposed, based on three interconnected models: a behavioral context model that integrates the characteristics of users, entities, and the environment; a behavioral distance model that assesses the deviation of current behavior from an individual reference profile; and an integrated risk indicator, which combines this deviation, the criticality of the asset, as well as the system context, and serves as an additional feature for predicting cyber incidents. The inclusion of the risk indicator made it possible to increase the F1-measure from 0.733 to 0.762, and the ROC-AUC from 0.937 to 0.965. At the same time, the share of false positives decreased by 54%. The resulting quality gain is due to the fact that the risk indicator characterizes not only the absolute values of behavioral features but the deviation of current actions from the individual user behavior model as well. An important result of the experiment is that the improvement in indicators was observed when using four different classification algorithms and was not inherent to a single model only. The designed framework could be implemented in information security monitoring systems and decision support systems. With continuous behavioral data, it could be used to quickly assess risk levels and detect potentially dangerous activity in a timely manner