The fast technological development has affected both the day-to-day operations of companies and the day-to-day activities of people living in this digital environment characterized by Industry 4.0. The lack of scalable and distributed architectures in the process of analyzing malware was the impetus for the present study. The novel Scalable Machine Learning Network (ScaleMalNet) proposed for malware detection. The framework designed to deal with malware in real time and on demand. utilizes a two-stage method of analysis: in the first stage, executable files are classified as malicious or legitimate based on static & dynamic analysis results; in the second stage, malicious executable files are classified into corresponding malware families based on static and dynamic analysis results. It offers the capacity to utilize Big Data approaches to handle a big number of malware samples. This study made use of two different kinds of conditioning information, both of which were put in the discriminator and the generator. One of the encoding mechanisms is the BASE + XOR combination. It is carried out in the generator of the work that has been proposed, and it results in lower overall energy consumption during data transmission. An objective is for comparison of the performance of traditional Machine Learning Approaches (MLA)s and Deep Learning (DL) architectures based on the range of different malware analysis models as a benchmark.