PREDICTIVE AI MODELS AND THEIR RELATIONSHIP TO PROTECTION AGAINST ADVANCED PERSISTENT THREATS TO THE FINANCIAL SYSTEM
DOI:
https://doi.org/10.24265/Keywords:
algoritmos inteligentes, amenazas persistentes avanzadas, aprendizaje automatico , ciberseguridad, inteligencia artificialAbstract
The objective was to establish the relationship between artificial intelligence (AI) predictive
models and protection against advanced persistent threats (APTs) in the Lima banking system by 2024. A secondary source analysis was conducted on AI predictive models that detect persistent cybersecurity threats such as malware. A survey was administered to a sample of 79 employees from banking institutions in Lima. The study was non-xperimental, quantitative, and cross sectional. The results showed improved performance of security systems in the banking sector after the application of predictive models in areas such as APT detection, mitigation, and prevention, thus strengthening cybersecurity in a critical context. These findings highlight the usefulness of the models in more accurately predicting attacks targeting financial institutions. The survey revealed that the majority of participants believe that AI predictive models help prevent APTs and optimize problem-solving, indicating a favorable trend toward the implementation of
AI-based tools within banks. Implementing predictive AI models strengthens banks’ resilience against APT attacks, as their ability to optimize processes improves resistance and has an effect on the evolution of protection against APT attacks, giving them adaptability to new threats as they improve and become more sophisticated.
Downloads
References
Abualhassan, Z., Hassan, E., Husni, D., Alothman, B., Shehata, N., Trabelsi, M., Shyha, I., Jaradat, S., & Al-Dubai, A. (2026). Malware ecognition using novel convolutional neural network with residual connections. International Journal Of Machine Learning And Cybernetics, 17(3). https://doi.org/10.1007/s13042-025-02815-6
Alageel, A., & Maffeis, S. (2026). Investigation of advanced persistent threats network based tactics, techniques and procedures. Computer Networks, 278, 112069. https://doi.org/10.1016/j.comnet.2026.112069
Almazarqi, H. A., Woodyard, M., & Marnerides, A. K. (2025). BotPro: Data-driven tracking & profiling of IoT botnets in the wild. Computers & Security, 162, 104778. https://doi.org/10.1016/j.cose.2025.104778
Arulkumar, D., & K, K. (2025). Metastack-aptnet: An ensemble deep learning framework for advanced persistent threat detection and mitigation in cyber-physical systems using blockchain technology. Computers & Electrical Engineering, 130, 110838. https://doi.org/10.1016/j.compeleceng.2025.110838
Banco Bilbao Vizcaya Argentaria S.A. ”BBVA ”. (2025, 10 de septiembre). La IA, en los dos lados de la ciberseguridad: aliada y amenaza en el mundo digital. BBVA. https://www.bbva.com/es/innovacion/la-ia-en-los-dos-lados-de-la-ciberseguridad-aliada-y-amenaza-en-el-mundo-digital/
Belali, F., Essetty, A., Bah, S., Wafi, I. E., & Daghouri, A. (2026). Design of a resilient multi-layered security framework for satellite communications. International Journal Of Information Security, 25(2). https://doi.org/10.1007/s10207-025-01184-z
Bodström, T., & Hämäläinen, T. (2026). Raw binary data usage with deep learning for advanced persistent threat attacks early stage detection. International Journal Of Machine Learning And Cybernetics, 17(2).
https://doi.org/10.1007/s13042-02502853-0
Choudhary, N., & Khaitan, V. (2026). Dependability Analysis of Cloud-Based VoIP Under an Advanced Persistent Threat Attack: A Semi-Markov Approach. Transactions On Emerging Telecommunications Technologies, 37(2). https://doi.org/10.1002/ett.70353
De la Hoz Suárez, B. A., Moran, I. F. L., Tete, A. E. M., & De la Hoz Suárez, A. I. (2024). Inteligencia artificial como
Estrategia para gestionar los procesos de auditoría financiera. Revista Estrategia Organizacional, 13(1), 57-72. https://doi.org/10.22490/25392786.7818
Deng, X., Li, P., Wang, C., Wang, R., Liu, Y., Han, W., & Tian, Z. (2026). A Stackelberg game based deception defense strategy against APT under resource constraints. Science China Information Sciences, 69(3). https://doi.org/10.1007/s11432-025-4530-7
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Héctor Martín Espinoza Villavicencio
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Creative Commons Atribución-NoComercial-CompartirIgual 4.0 Internacional (CC BY-NC-SA 4.0). Faculta a los usuarios a compartir: copiar y redistribuir el material en cualquier medio o formato y adaptar: remezclar, transformar y desarrollar el material, siempre y cuando se acredite al autor original, no se utilice con propósitos comerciales y las nuevas creaciones se licencien bajo los mismos términos de esta licencia.
