Enhancing and Evaluating Malware Detection: File Malware Detection using Numerous Machine Learning Methods

Malware detection is the process of identifying and preventing malware from harming a system, network, or device. This process leverages various algorithms and techniques to identify and classify malicious software. ​Machine Learning (ML) techniques are increasingly being explored to improve malware detection as cyber threats become more sophisticated. ​Traditional signature-based detection methods are often insufficient against advanced malware that uses evasion tactics like polymorphism and metamorphism. ​ML-based malware detection models include supervised, unsupervised, and reinforcement learning approaches. ​An evaluation of these models on various datasets helps determine their effectiveness in identifying malicious code. In this paper, we study the use of ML techniques in enhancing malware detection amidst the evolving landscape of cyber threats. Our study introduces a taxonomy of ML-based malware detection models and conducts an evaluation of these models on various datasets to determine their effectiveness in identifying malicious code. We also introduce a recent survey on file malware detection that studies more sophisticated attacks. Our findings offer insights for developing more resilient and intelligent malware detection systems and address the challenges of integrating these models into real-world cybersecurity systems.