Oleksii Chalyi

Mr. Oleksii Chalyi

Vilnius University, Vilnius, Vilniaus Miestas, Lithuania
orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
1 June 2024 in InfoScience Trends
Verified
Journal Article
Open access
PDF file
Oleksii ChalyiOleksii Chalyi
Oleksii Chalyi
This article presents a thorough examination of eight state-of-the-art AI chatbots that are designed for general use. Through detailed descriptions and empirical research, which include the use of confusion matrices and a pairwise comparison methodology, the study systematically assesses these chatbots based on eight specific criteria. The main objective of this research is to pinpoint the most efficient AI chatbot for general purposes, thereby providing invaluable insights for both users and developers within the AI industry. By utilizing the results of this study, developers can gain access to crucial information and actionable recommendations that help in enhancing the performance of their chatbots. Furthermore, these findings act as a vital resource for budding developers who are venturing into the creation of their own chatbot projects. In a rapidly evolving technological landscape, where AI is increasingly infiltrating various aspects of daily life, such detailed evaluations play a crucial role. They guide both users and developers towards selecting and developing AI chatbots that are not just effective, but also user-friendly and adaptable to the shifting needs and preferences of their user base.

25 February 2025 in Future Internet
Verified
Journal Article
Open access
PDF file
Oleksii ChalyiOleksii Chalyi
Oleksii Chalyi
KDKestutis Driaunys
Kestutis Driaunys
Vytautas RudžionisVytautas Rudžionis
Vytautas Rudžionis
This study systematically evaluates the vulnerabilities of modern web browsers using developed indices derived from the CVE database, including ICVE, ICVSS, IR and IT. These indices incorporate metrics such as vulnerability severity and risks, along with browser popularity, to enable a balanced comparison of browser security. The results highlight significant differences in browser security: while Google Chrome and Samsung Internet exhibited lower threat indices, Mozilla Firefox demonstrated consistently higher scores, indicating greater exposure to risks. These observations a slightly contradict widespread opinion. The findings emphasize the importance of timely software updates in mitigating vulnerabilities, as many incidents were linked to outdated browser versions. This study also introduces a robust methodology for assessing browser threats, providing a framework for future research. Potential applications include developing browser-based penetration testing systems to simulate phishing and data extraction scenarios, offering insights into user-specific risks and broader organizational impacts. By combining theoretical analysis with practical implications, this work contributes to advancing browser security and lays the foundation for future applied research in cybersecurity.

14 December 2022 in Theoretical and Applied Cybersecurity
Verified
Journal Article
Open access
PDF file
Oleksii ChalyiOleksii Chalyi
Oleksii Chalyi
MKMyhailo Kolomytsev
Myhailo Kolomytsev
For a long time, threat of web-application authentication break remained a problem not only for users but also for business. This threat still exists, since broken authentication provides a blackhat with full access to accounts of users and business data. This article analyzes software tools for breaking authentication as well as it defines time required for breaking-in depending on different conditions. Based on the results of the analysis, the fastest tool was determined. In order to complete this analysis and determine the fastest tool, own web-application was created.

1 January 2025 in Baltic Journal of Modern Computing
Verified
Journal Article
Closed access
Oleksii ChalyiOleksii Chalyi
Oleksii Chalyi

1 January 2024 in Cybersecurity: Education, Science, Technique
Verified
Journal Article
Open access
PDF file
Oleksii ChalyiOleksii Chalyi
Oleksii Chalyi
ISIryna Stopochkina
Iryna Stopochkina
Information about cyberattacks that attackers plan to carry out against critical infrastructure facilities is partly distributed on malicious information сhannels, chats or sites. Investigation of information materials and their analysis can provide an understanding of the stages of attack planning and their prevention. Part of this problem is to provide information search and analysis tools to detect linguistic patterns, similarities in text data, which are capable of deanonymizing cybercriminals and establishing relationships between published data. This work proposes a new model and a corresponding prototype of the system, based on the vector space model and the TF-IDF algorithm. The system is designed to analyze publicly available text data (both internet and darknet), and differs with a probabilistic approach to analyzing the identifiers of the information publisher. The proposed system also focuses on identifying latent connections between anonymous accounts by analyzing unique stylistic and linguistic traits. It leverages these traits to trace patterns in communication, uncovering hidden associations among cybercriminal entities. Experiments conducted based on the analysis of real chats, including chats of cybercriminals, demonstrate the potential of the system for detecting identifiers and determining stylistic features. If a sufficiently complete set of data is available and a list of target words is available, it is possible to analyze the stages of preparing an attack, malicious individuals or groups involved in it. The results underline the significance of integrating advanced linguistic analysis techniques with probabilistic models to enhance investigative capabilities against evolving cyber threats.

19 March 2026 in Electronics
Verified
Journal Article
Open access
PDF file
Oleksii ChalyiOleksii Chalyi
Oleksii Chalyi
KDKestutis Driaunys
Kestutis Driaunys
Šarūnas GrigaliūnasŠarūnas Grigaliūnas
Šarūnas Grigaliūnas
RBRasa Bruzgiene
Rasa Bruzgiene
This paper presents a standard-oriented architecture for automating information security risk management (ISRM) using artificial intelligence. The study first evaluates eight international frameworks (including COBIT 2019, NIST SP 800-53, and ISO 31000) for automation suitability, identifying ISO/IEC 27005 as the optimal structural foundation. Based on these findings, an architecture integrating Natural Language Processing and machine learning to automate risk identification, assessment, and treatment is proposed. A core component is a decision-making module that combines expert reasoning with a Multi-LLM consensus mechanism to ensure reliability. To provide exploratory support for the proposed architecture, a comparative study using five state-of-the-art Large Language Models (ChatGPT, Gemini Advanced, Grok, Microsoft Copilot, and DeepSeek Chat) was conducted on a standardized risk identification task. The results highlight strong cross-model consensus patterns, providing exploratory evidence that LLMs may support expert-informed risk identification and reasoning tasks while acknowledging the current limitations in complex reasoning. This approach proposes a transparent architectural foundation for AI-driven ISRM whose scalability must be established through future prototype-based evaluation, thereby bridging the gap between rigid compliance standards and generative AI capabilities.