Leveraging dynamic embeddings and reinforcement learning with bayesian networks for ransomware resiliences
Year: 2025
Type: article
Abstract: Ransomware has emerged as a formidable cybersecurity menace, targeting organizations and individuals with devastating consequences. This research paper delves into the multifaceted domain of ransomware resilience, investigating advancements in detection and mitigation strategies to combat realworld threats effectively. The study begins with a comprehensive literature review, shedding light on the evolving tactics of ransomware perpetrators and the limitations of traditional security measures. Drawing insights from diverse data sources, including incident reports and surveys, the research analyzes historical ransomware attacks, uncovering trends, attack vectors, and vulnerable sectors. In pursuit of improved detection capabilities, the paper explores cutting-edge approaches such as behavior-based analysis and machine learning algorithms. Deception methods and honeypots are investigated as additional layers of defense to divert attackers and minimize the impact of potential breaches.
Source: Cyber Security and Applications
Language: English
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4409852057