COMPREHENSIVE ANALYSIS OF MALWARE: APPROACHES, CHALLENGES AND PROSPECTS
DOI:
https://doi.org/10.32689/maup.it.2025.4.14Keywords:
malware, static analysis, dynamic analysis, hybrid analysis, automation, machine learning, cybersecurityAbstract
The purpose of this study is to systematize and analyze modern methods for examining malicious software (malware) in the context of cybersecurity. The paper focuses on determining the effectiveness of different approaches to malware analysis, identifying their strengths and limitations, and assessing prospects for the development of tools and methodologies aimed at countering evolving cyber threats. Particular attention is paid to an integrated approach that combines traditional and modern technologies, including machine learning methods and automation of analysis processes. Methodology. The study applies a systematic approach to malware examination, which includes static, dynamic, and hybrid analysis. In addition, the research involves the analysis of automated platforms and machine learning techniques used for classifying and predicting the behavior of malicious samples. The practical part is based on the examination of well-known threat cases such as WannaCry, TrickBot, and Emotet, which demonstrate the use of combined methods to obtain reliable and verifiable results. The scientific novelty of this work lies in the comprehensive comparison of existing malware analysis methods, identification of their advantages and limitations in the context of modern cyber threats, and the determination of prospects for integrating traditional approaches with intelligent analysis systems based on machine learning. The study emphasizes the importance of employing a hybrid approach and automated laboratory environments to improve the accuracy and safety of malware analysis. Conclusions. The results of the study demonstrate that effective malware analysis requires a combination of static, dynamic, and hybrid methods, the application of modern automation tools, and the integration of artificial intelligence technologies. The practical implementation of combined methods allows for forming a holistic understanding of cyber threats, identifying hidden attack mechanisms, and predicting potential risks. A comprehensive approach to malware analysis is a key element in the information security system, ensuring the reliability of protective mechanisms and forming a foundation for strategies to counter modern cyber threats. The paper underlines the necessity of continuously improving analytical methods, expanding international cooperation, and integrating advanced technologies to ensure timely responses to evolving threats in the digital environment.
References
Beleа A.-R. Methods for Detecting Malware Using Static, Dynamic and Hybrid Analysis. International Conference on Cybersecurity and Cybercrime. 2023. Vol. 10(2023). https://doi.org/10.19107/CYBERCON.2023.34
Jusoh R., Firdaus A., Anwar S., Osman M.-Z., Darmawan M.-F., Ab Razak M.-F. Malware detection using static analysis in Android: a review of FeCO (features, classification, and obfuscation). PeerJ Comput. 2021. Sci. 7:e522 http://doi.org/10.7717/peerjcs.522
Lee, Deepak Tomar A., Verma K., Chhillar A. Hybrid Static-Dynamic Malware Analysis Framework Using Interpretable Neural Network. International Journal of Scientific Research in Engineering and Management. 2025. Vol. 09, Issue 09. https://doi.org/10.55041/IJSREM52505
Leon R. S., Kiperberg M., Zabag A. L., Zaidenberg N. Hypervisor-assisted dynamic malware analysis. Cybersecurity, 2021. Vol. 4, Article 19(2021). https://doi.org/10.1186/s42400-021-00083-9
Nafiev A. E., Rodionov A. M. Malware dynamic analyses system based on virtual machine introspection and machine learning methods. Problems in Programming. 2023. № 2. Р. 84–90. https://doi.org/10.15407/pp2023.02.084
Shevchenko А., Zastelo Н., Shpachinskiy Y. Analysis of application a methods of machine learning based on artificial neural networks in the tasks of detecting cybersecurity threats. Information Technology and Security. 2019. Vol. 7. № 1 (12). Pp. 79–90. https://doi.org/10.20535/2411-1031.2019.7.1.184327
Sihwail R., Omar K., Zainol Ariffin K. A. A Survey on Malware Analysis Techniques: Static, Dynamic, Hybrid and Memory Analysis. International Journal on Advanced Science, Engineering and Information Technology. Vol. 8, No. 4-2, Pp. 1662–1671. http://doi.org/10.18517/ijaseit.8.4-2.6827
Vladov S., Jotsov V., Sachenko A., Prokudin O., Ostapiuk A., Vysotska V. Neural Network Method of Analysing Sensor Data to Prevent Illegal Cyberattacks. Sensors. 2025, 25(17), 5235; https://doi.org/10.3390/s25175235
Vladov S., Vysotska V., Lytvyn V., Komziuk A., Prokudin O., Ostapiuk A. Adaptive Neural Network System for Detecting Unauthorised Intrusions Based on Real-Time Traffic Analysis. Computation Open source preview, 2025, 13(9), 221. https://doi.org/10.3390/computation13090221
Vladov S., Vysotska V., Varlakhov V., Nazarkevych M., Bolvinov S., Piadyshev,V. Innovative Method for Detecting Malware by Analysing API Request Sequences Based on a Hybrid Recurrent Neural Network for Applied Forensic Auditing. Applied System Innovation (ASI). 2025, 8(5), 185. DOI: 10.3390/asi8050156
Voskoboinyk V., Savchenko Iu., Karpukov L., Parshyna O., Prokopovych-Tkachenko, D. Assessment of the state of information security using expert systems. Systems and Technologies, 2024, 67(1), 72–79. https://doi.org/10.32782/2521
Гапон А. O. Експериментальне дослідження, програмна реалізація та оцінка ефективності застосування методу захисту програмного забезпечення на основі гібридного аналізу. Сучасний захист інформації. № 3(63). С. 27–36. https://doi.org/10.31673/2409-7292.2025.030422
Єгоров С. В., Шкварницька Т. Ю. Розширений метод аналізу шкідливого програмного забезпечення з метою створення сигнатур. Вісник Університету «Україна», № 1 (24), 2020. С. 161–170. https://doi.org/10.36994/2707-4110-2020-1-28-14
Жульковська І., Плужник А., Жульковський О. Сучасні методи виявлення шкідливих програм. Математичне моделювання. 2021. №1(44). С. 46–54. https://doi.org/10.31319/2519-8106.1(44)2021.235922
Сініцин І., Рогушина Ю., Бова Ю. Розробка семантичних засобів підтримки процесу авторизації безпеки інформаційних систем. Вісник Кременчуцького національного університету імені Михайла Остроградського. Випуск 4 / 2025(153). С. 249–264. https://doi.org/10.32782/1995-0519.2025.4.28






