Comparison of Malware Detection Techniques Using Machine Learning Algorithms

With the intricacy of malware evolving as quickly as innovation advances, the conflict between security researchers and malware writers is never-ending. Cyber-attacks and therefore the use of malware are increasingly ubiquitous these days. States or a publicly traded firm is the examples of targets. Malware analysis has become a critical component of incident response for computer security issues. During forensics investigations, organizations are frequently presented with strange records gathered by their antiviral and security monitoring systems. Most arrangements suspiciously leak multiple tactical files through various strategies involving both inactive and active procedures in order to identify malware. However, these mechanisms have numerous limitations that give rise to an unused inquire about track. The point of this paper is to handle the utilization of machine learning calculations to analyze malware and uncover how information science is utilized to detect malware. Attack-detection training systems enable the development of better protection tools that can detect attacks and unprecedented campaign. This research demonstrates that a variety of models can be utilized to determine their detect ability. The findings of our example show that malware can be analyzed using a variety of machine learning techniques (ML) algorithm to compare them. On a short dataset, the result shows that the decision tree algorithm has the best detection accuracy when compared to other classifiers, with 99 and 0.021% false positive rate (FPR).