COMPARATIVE ANALYSIS OF RANSOMWARE DECRYPTION METHODS
Ransomware is one of the most serious cybersecurity threats, as it can have a devastating impact on private users, businesses and government agencies alike. This survey paper analyses current ransomware decryption techniques, which include approaches such as brute-force, vulnerability analysis, specialised decryptors and machine learning techniques. The aim of the study is to provide a comprehensive analysis of existing methods to determine their effectiveness, resource costs and limitations. Particular attention is given to methods utilising artificial intelligence due to their significant potential in improving decryption efficiency and developing adaptive solutions. The analysis shows that machine learning and AI can significantly accelerate vulnerability detection and improve decryption accuracy. The results of the study highlight the importance of leveraging these advanced technologies to better protect systems from threats posed by ransomware. The practical relevance of the paper is that it provides cybersecurity professionals with valuable insights into the selection of appropriate defence techniques and possible ways to improve them. The article also reveals directions for future research, focusing on the need to develop more versatile and effective defence tools. The authors demonstrate that integrating new technologies into existing approaches can significantly reduce risks and increase the resilience of systems. Thus, the presented material contributes to the knowledge and understanding of modern decryption techniques and their role in combating ransomware, making it an important contribution to the development of the industry.
Authors
- Zhanar Akhmetova (ORCID: https://orcid.org/0000-0002-5483-5260)
- Bulat Serimbetov (ORCID: https://orcid.org/0000-0003-4675-4388)
- Peter Popov
- Dias Zhaksybek
Publication Details
- Journal
- Bulletin of D Serikbayev EKTU
- Published
- 2025-03-30
- DOI
- https://doi.org/10.51885/1561-4212_2025_1_138
- Primary Topic
- Advanced Malware Detection Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00