Security Enhanced Cloud Computing Using the Integration of Dense Belief Network and
RK-AES Algorithm

Introduction/BLUF:
The article by Al-Sadarini et al. (2025) examines how cloud security can be improved by
combining deep learning with encryption methods. As cloud computing becomes more
widely used for storing sensitive information, the risk of cyberattacks also increases. The
authors introduce a hybrid framework called AES-RKDBN that detects intrusions using a
Dense Belief Network and encrypts data using an enhanced AES method before it is stored.

BLUF:
The study concludes that integrating intrusion detection with encryption improves cloud
security performance compared to existing deep learning models.

Research Question, Hypothesis, IV and DV:
The main research question asks whether combining a Dense Belief Network with the RK-
AES algorithm improves cloud security effectiveness. The hypothesis is that this integrated
model will outperform existing systems in detecting and preventing intrusions.
The independent variable is the implementation of the AES-RK-DBN framework. The
dependent variables include measurable security outcomes such as accuracy, detection
rate, sensitivity, recall, and overall system performance.

Research Methods and Data Analysis:
The study uses a quantitative experimental design. The researchers tested their model
using cloud security datasets and compared the results to other deep learning approaches
such as LSTM and CNN-based models.
Performance was evaluated using statistical measures including detection accuracy,
specificity, recall, and f-score. By comparing measurable results across models, the
authors were able to determine whether their system performed more effectively.

Connection to Social Science and Course Concepts:
Although technical, this study connects to social science principles because cybersecurity
affects trust, risk, and institutional responsibility. Cloud users must trust providers to
protect sensitive information. When security fails, it impacts businesses and individuals
socially and economically.
The article also connects to Routine Activities Theory. Cybercrime occurs when there is a
motivated offender, a suitable target, and a lack of capable guardianship. The proposed
framework strengthens guardianship by improving detection and encryption.

Reinforcement Sensitivity Theory is also relevant. Individuals who are impulsive or reward
driven may engage in cybercrime if the perceived benefits outweigh the risks. Stronger
detection systems reduce successful attacks and increase perceived risk.

Marginalized Groups and Conclusion:
Improving cloud security benefits marginalized communities who rely on affordable cloud
services and may lack resources to recover from cyberattacks. Stronger encryption and
detection help protect sensitive data from exploitation.
In conclusion, the study contributes to society by improving cloud security through an
integrated technical approach that strengthens digital trust and reduces opportunities for
cyber offending.

References:
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