Deep Neural Network Binary Classification for Malware Detection: A Parametric Study

In the face of escalating digital threats, the precise identification of malware stands as a significant security imperative. Our investigation delves into a meticulous parametric analysis of the Deep Neural Network (DNN) architecture, yielding marginally enhanced performance compared to previous literature findings. While our improvements are subtle, they underscore the significance of parametric optimization in bolstering the efficacy of detection models. These findings emphasize the necessity for continuous, state-of-the-art research endeavors aimed at honing existing techniques, promising optimistic avenues for safeguarding information technology systems amidst the burgeoning landscape of digital threats.