SecFedMDM-1: A Federated Learning-Based Malware Detection Model for Interconnected Cloud Infrastructures
Daniella Mughole Kalimumbalo, Joke A. Badejo, Kennedy Okokpujie, Emmanuel Adetiba, Molo Mbasa Joaquim, Nzanzu Vingi Patrick, Gabriel Oyeyemi, Claude Takenga · IEEE Access · 2025
Enforcing security and reliability in the cloud is a challenging but vital task because of the multitude of heterogeneous applications utilising the same infrastructure. Integrating a security analysis system to identify and mitigate potential threats, such as malicious software (Malware), is crucial for the effective functioning of cloud infrastructures. Over the past few decades, new malware analysis and detection approaches have emerged because of various malware strategies that evade host- and network-based security measures. This study established a federated learning-based malware detection model for interconnected cloud infrastructures. This method protects users’ privacy as numerous devices can collaborate to build machine learning models without sharing data. Three distinct deep-learning algorithms were chosen for the models’ training, validation, and testing phases. With the training of eight clients and twenty-five federation rounds, the FeedForward Neural Networks (FFNN) model performed best. It had accuracy, an F1-score, and a precision of 84%, while the Multi-Layer Perceptron (MLP) model performed with 83% accuracy, 83% F1-score, and 83% precision, and the Long Short-Term Memory (LSTM) model performed with 80% accuracy, 80% F1-score, and 80% precision.