Article Review Security Enhanced Cloud Computing Using the Integration of Dense
Belief Network and RK-AES Algorithm
Student Name: Keeon Allen
School of Cybersecurity, Old Dominion University
CYSE 201S: Cybersecurity and the Social Sciences
Date: 11\/14\/25<\/p>\n\n\n\n
<\/p>\n\n\n\n
Introduction
This article examines the growing security vulnerabilities in cloud computing and
proposes a combined deep learning and encryption framework to enhance data protection.
The bottom line up front: the AES-RK-DBN model increases detection accuracy,
improves encryption strength, and provides a scalable security solution for modern cloud
systems.
Relation to Social Science Principles
Cloud security is fundamentally connected to social science principles because
technology directly influences human behavior, organizational structures, trust, and risk
perception. The article aligns principles such as culture, interactions, social systems, and
ethical decision making. User trust in institutional policies, and social behavior around
adoption of cloud services all depend on whether security is strong and reliable.
Research Question, Hypothesis, Independent & Dependent Variables
Research Question: Can integrating an enhanced AES encryption algorithm with a
Dense Belief Network improve cloud security and intrusion-detection accuracy?
Hypothesis: The authors hypothesize that the AES-RK-DBN system will outperform
existing deep-learning architectures in identifying malicious activity.
Independent Variable: The security model used (AES-RK-DBN vs. other DL models.
Dependent Variable: System performance outcomes, including detection accuracy,
sensitivity, specificity, F-score, and encryption effectiveness.<\/p>\n\n\n\n
<\/p>\n\n\n\n
Types of Research Methods Used
The study uses quantitative research methods to evaluate security performance.
Data was obtained from established intrusion-detection datasets (KDDCup99, NSL-
KDD, UNSW-NB15). The researchers conducted computational experiments to compare
multiple models under identical conditions. No qualitative human-subject data was
collected.
Types of Data and Analysis Used
Data consisted of labeled intrusion-detection records. Analysis techniques
included Principal Component Analysis (PCA) for dimensionality reduction, statistical
performance measurement and computational benchmarking across several deep-learning
architectures. The quantitative comparisons allowed the authors to validate improvements
in performance and efficiency.
Connections to Course Concepts
The article connects directly to course concepts such as risk, threat modeling,
confidentiality, data governance, and human-technology interaction. Course materials
emphasize how cybersecurity problems exist within social systems and how human
decisions shape technological outcomes. The study reinforces lessons about the
importance of designing systems that balance security with usability and reliability. It
also aligns with course discussions of AI-supported defense mechanisms and the role of
encryption in maintaining trust in digital environments.<\/p>\n\n\n\n
<\/p>\n\n\n\n
Connections to Marginalized Groups
Cloud security impacts marginalized groups by shaping access to safe digital services,
financial platforms, healthcare portals, and communication tools. Weak cloud security
disproportionately harms communities already at higher risk of surveillance, data misuse,
and identity theft. While the article does not explicitly focus on marginalized groups, its
contributions indirectly support them by improving confidentiality, reducing
unauthorized monitoring, and promoting equitable data protection across user
populations.
Overall Societal Contributions \/ Conclusion
This study advances society\u2019s understanding of secure cloud infrastructures by
demonstrating that integrating encryption with intelligent intrusion detection improves
both efficiency and accuracy. Stronger cloud security increases public trust, supports
economic growth, and enhances data privacy for individuals and organizations. The AES-
RK-DBN model provides a foundation for future research in intelligent cybersecurity
systems and contributes to building a safer, more resilient digital environment.<\/p>\n\n\n\n
<\/p>\n\n\n\n
Reference
Al-Safarini, M. Y., Al-Milli, N., Maghrabi, L. A., & Elian, M. (2025). Security Enhanced
Cloud Computing Using the Integration of Dense Belief Network and RK-AES Algorithm.
International Journal of Cyber Criminology, 19(1), 154\u2013179.
Article Link: https:\/\/www.cybercrimejournal.com\/Al-
Safarinietalvol19issue1IJCC2025.p<\/p>\n","protected":false},"excerpt":{"rendered":"
Article Review Security Enhanced Cloud Computing Using the Integration of DenseBelief Network and RK-AES AlgorithmStudent Name: Keeon AllenSchool of Cybersecurity, Old Dominion UniversityCYSE 201S: Cybersecurity and the Social SciencesDate: 11\/14\/25 IntroductionThis article examines the growing security vulnerabilities in cloud computing andproposes a combined deep learning and encryption framework to enhance data protection.The bottom line up… <\/p>\n