Use of Machine Learning against Malware Attacks in the Banking Sector

Chavez Alvarez D.M.; Riqueros Carhuayal I.N.; Ayala Ñiquen E.E.; Yactayo Arias C.A. · Proceedings of the LACCEI international Multi-conference for Engineering, Education and Technology (2025) · DOI: 10.18687/leird2025.1.1.864

Resumen

Cyber threats and risks associated with digital security have increased considerably in the banking sector, driving the need to adopt new technologies that allow detecting and mitigating potential attacks. This review aims to identify the most widely used machine learning models against malware detection. Method: 194 original articles related to the subject were analyzed, of which only 27 met the inclusion criteria for the final review. Additionally, a dynamic analysis was used to examine the performance of the algorithms in real and simulated scenarios. It was evident that Machine Learning models, particularly supervised learning models such as neural networks, support vector machines, and random forest algorithms, have achieved promising results in the early detection of malware, allowing for a faster and more accurate response to potential cyber threats. The integration of Machine Learning into banking cybersecurity has generated significant advances in the identification and control of malicious attacks, provided that there is adequate data quality, constant updating of the models, and proper coordination with existing defense systems. Therefore, it is concluded that the use of these technologies, beyond their technical capacity, also represents an opportunity to strengthen the culture of prevention and digital resilience within the financial environment. © LEIRD 2025.All rights reserved.

Instituciones: Universidad Tecnológica del Perú