Real-Time Malware Detection in Cloud Infrastructures Using Convolutional Neural Networks: A Deep Learning Framework for Enhanced Cybersecurity

This study presents a novel malware detection framework for cloud infrastructures that harnesses the power of Convolutional Neural Networks (CNNs) to achieve real-time threat identification with superior accuracy and speed. Our approach begins with the collection and meticulous preprocessing of heterogeneous cloud log data, followed by advanced feature engineering to extract meaningful patterns indicative of malicious activity. The CNN model automatically learns hierarchical representations from this high-dimensional data, resulting in a detection system that achieves an accuracy of 98.2%, a precision of 97.5%, a recall of 98.0%, and an F1-score of 97.8%. In addition, the model operates with a low latency of 12 ms, a critical factor for timely threat mitigation in dynamic cloud environments. Comparative analysis against Long Short-Term Memory (LSTM), Support Vector Machine (SVM), and Random Forest classifiers reveals that the CNN not only outperforms these models in key performance metrics but also maintains a significant advantage in processing speed. These findings highlight the potential of CNN-based approaches to enhance cybersecurity defenses, offering a scalable and efficient solution for detecting evolving malware threats in cloud infrastructures.