Application of Machine Learning Techniques for Risk Management Against Malware Attacks in the Business Sector

Abstract

This study aims to analyze the use of machine learning for detecting and preventing malware attacks in key technological environments such as IoT, enterprise networks, and critical systems. A comprehensive review of deep learning techniques and models applied in cybersecurity is conducted, evaluating their effectiveness, accuracy, and the limitations they face against emerging threats. The review also aims to identify the most innovative solutions that integrate artificial intelligence to enhance cyber defenses. To carry out this RSL, a methodological approach was followed, which included collecting relevant articles from academic databases, applying inclusion and exclusion criteria to ensure the quality of the selected studies. Key data was extracted and analyzed from the reviewed works, organized by the machine learning techniques used and the specific areas of application. The results showed that deep learning techniques and hybrid models have significantly improved the detection and mitigation of advanced attacks, such as ransomware and APTs. However, important challenges in implementing these technologies were identified, especially in sectors with resource limitations and resistance to organizational change. In conclusion, the use of machine learning has proven to be highly effective in improving cybersecurity, although its widespread adoption still faces barriers such as the lack of trained personnel and adequate infrastructure. This study highlights the need for further research into integrating these technologies with emerging solutions and improving their adaptability across different organizational contexts.