In this work, an efficient machine learning-based approach is taken up: Random Forest, which identifies the efficiency of this very approach in distinguishing malware from original applications based on the content of the PE file. It deals with broad characteristics that have been taken from the PE files for training and tests by using a dataset with labeled examples of both kinds. Such may include the accuracy, precision, and recall among other metrics that shall be used through this experimentation phase, testing the efficacy of the Random Forest classifier in distinguishing the two categories. It also shows how to use the model in the Graphical User Interface to make predictions with regard to the PE files in an easily understandable way by users. These findings convey how machine learning approaches, especially Random Forest, potentially enhance cybersecurity methods through efficient detection of malware.