Deep Learning Techniques for Threat Detection in Cloud Environments: A Review
Iman Youssif Ibrahim *
Technical College of Informatics, Akre University for Applied Sciences, Duhok, Kurdistan Region, Iraq.
Hajar Maseeh Yasin
Technical College of Informatics, Akre University for Applied Sciences, Duhok, Kurdistan Region, Iraq.
*Author to whom correspondence should be addressed.
Abstract
Deep learning techniques have become essential in enhancing threat detection within cloud environments, offering the ability to process large-scale data and detect complex patterns. As cloud computing continues to grow, ensuring robust security measures is critical to protecting sensitive data from evolving cyber threats. Deep learning models, particularly CNN, RNN, and Autoencoders, play a key role in identifying various threats, such as unauthorized access, data leakage, and DDoS attacks. This paper reviews research published between 2018 and 2023, comparing the effectiveness of deep learning models in cloud security. The findings indicate that deep learning models provide higher accuracy and adaptability compared to traditional methods. However, challenges such as data confidentiality, high computational requirements, and real-time detection still persist. The paper concludes by highlighting the need for hybrid models and enhanced training datasets to overcome these challenges. This review is valuable for researchers and practitioners working to implement deep learning approaches in cloud security.
Keywords: Deep Learning, threats, cloud security, cyber security