Enhancing Cloud Network Security With Hybrid Cnn-Lstm Models for Intrusion Detection

Currently, cloud computing has become the next big thing with every other important service being provided by cloud but that also brings critical security challenges. This paper focuses on Artificial Intelligence (AI) and Machine Learning (ML), its main contribution to an Intelligent Intrusion Detection System for Better Cloud Security. This problem is addressed in this study with the use of hybrid Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) model, which combines the more meritocratic behaviors to detect anomalies while having increased level on accuracy as well quicker response time. This study addresses this challenge using a hybrid Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) model that combines the strengths of both architectures for effective anomaly detection and response with increased accuracy and quick response time. It assisted the model and was tested on NSL-KDD, observing different evaluations like accuracy, precision recall, F1 score. The experimental results show that the proposed model can even deal with intrusions of multiple attack categories which proves it to be a potential tool in strengthening cloud security frameworks. Importantly, the results validate the competitive reliance on AI/ML IDS solutions to proactively and adaptively defend against cybersecurity threats in Clouds and provide a foundation to leverage these findings for future advancements in adaptive security measures.