• Malvin Ojong Ndipawoh
• Er. Rupali

Cloud computing has become ubiquitous in modern IT infrastructure due to its scalability, flexibility, and cost-effectiveness, with over 94% of enterprises using cloud services. However, the security of cloud applications remains a significant concern due to the potential for various threats and attacks, with 75% of organizations experiencing at least one cloud security incident in the past year. This research proposes a comprehensive approach for intelligent threat detection and prevention in cloud applications, addressing the unique security challenges posed by shared and dynamic cloud environments. The proposed approach integrates traditional security measures with advanced machine learning techniques to enhance the security posture of cloud applications. By leveraging machine learning algorithms for real-time threat detection and classification based on analysis of network traffic, system logs, and user behavior, the approach aims to identify and mitigate a wide range of cyber threats, including malware, data breaches, and DDoS attacks. Our models, including Random Forest, Gradient Boosting, and Decision Tree, achieved high detection accuracy, with Random Forest and Gradient Boosting reaching an AUC of 0.98. The effectiveness of the proposed approach is evaluated through extensive experimentation in simulated cloud environments using the UNSW NB15 dataset and realistic attack scenarios. Experimental results demonstrate the superiority of the approach in terms of performance metrics such as detection accuracy, precision, recall, F1-score, and response times. Notably, the Random Forest model achieved an accuracy of 87.34%, a precision of 82.07%, a recall of 98.54%, and an F1-score of 89.55. Additionally, the average response time was significantly reduced to 2.3 seconds, compared to 5.6 seconds for traditional security measures. Overall, this research contributes to the advancement of cybersecurity in cloud applications by proposing a comprehensive approach that combines traditional security measures with advanced machine learning techniques. By addressing the unique security challenges of cloud environments, the proposed approach enhances the resilience of cloud applications against emerging cyber threats and contributes to the overall security and trustworthiness of cloud computing infrastructure.

Cloud Computing, Cloud Applications, Threat Detection, Threat Prevention, Machine Learning, Data Privacy, Data Integrity, Compliance, Cybersecurity

"Enhancing Security in Cloud Applications through Machine Learning-Based Threat Detection and Prevention", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 7, page no.b216-b224, July-2024, Available :http://www.jetir.org/papers/JETIR2407126.pdf

"Enhancing Security in Cloud Applications through Machine Learning-Based Threat Detection and Prevention", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 7, page no. ppb216-b224, July-2024, Available at : http://www.jetir.org/papers/JETIR2407126.pdf