Malware Detection Employing Deep Neural Networks

Malware, malicious software designed to disrupt, damage, or gain unauthorized access to computer systems, poses a significant and evolving threat to cybersecurity. Malware detection is an essential component of modern cybersecurity, given the escalating complexity and diversity of malicious software threats. In this study, we present a novel approach to malware detection based on behavior-based datasets using a fully connected deep neural network. Our research is motivated by the need for robust and accurate malware detection models that can adapt to evolving threats. The behavior-based dataset, which captures the dynamic interactions of malware with the host environment, provides a rich source of information for training and evaluation. The model uses the hyperbolic tangent (tanh) activation function and the Nesterov optimizer, resulting in remarkable accuracy of 100%. This study offers a high- performing solution for malware detection using behavior- based datasets. As cybersecurity continues to evolve, our approach contributes to strengthening defenses against the ever- persistent threat of malware.