Spyware in Smartphones: Bibliometric Analysis
DOI:
https://doi.org/10.61799/2216-0388.1740Keywords:
Android, Bibliometric, Malware, Spyware, SmartphoneAbstract
Spyware is a latent threat within the Android operating system, whose open architecture facilitates the installation of malicious applications capable of collecting sensitive data without authorization. This issue has attracted the attention of the scientific community, driving the development of solutions based on artificial intelligence and machine learning. The main objective of this study was to analyze, through a bibliometric approach, the evolution of scientific production on spyware in Android. Publications were selected from IEEE, ACM, Scopus, and Google Scholar, based on specific inclusion and exclusion criteria. The analysis, conducted using Bibliometrix and VOSviewer, revealed that 66% of the publications were concentrated prior to 2020, with notable peaks in 2018 and 2020. A subsequent decline was observed, followed by a resurgence in 2023 and 2024. Approximately 80% of the articles focused on techniques based on AI and machine learning, confirming the predominance of these methodological approaches. Geographically, the United States led with 23% of the publications, followed by Italy with 17%, both also standing out for their strong participation in international collaboration networks. It is concluded that research on spyware in Android remains active and technologically advanced, although it continues to face challenges due to the evolving nature of threats, weak regulatory frameworks, and limited digital awareness among users. It is recommended to strengthen the development of adaptive detection models, promote cybersecurity training strategies for end users, and critically review mobile data protection policies—especially in vulnerable contexts such as the Android ecosystem.
Downloads
References
[1] Martín, I., Hernández, J. A., Muñoz, A., y Guzmán, A., «Android malware characterization using metadata and machine learning techniques», arXiv:1712.04402. [En línea]. Disponible en: https://arxiv.org/abs/1712.04402
[2] A. Hefter, C. Sendner y A. Dmitrienko, “Metadata‑based Malware Detection on Android using Machine Learning,” arXiv preprint arXiv:2307.08547, Jul. 2023. DOI disponible en: https://arxiv.org/abs/2307.08547
[3] Kaur, A., Lal, S., Goel, S., Pandey, M., y Agarwal, A., «Android Malware Detection System using Machine Learning», presentado en Proceedings of the 5th International Conference on Sustainable Computing, ACM, 2024. doi: 10.1145/3675888.3676049. [En línea]. Disponible en: https://dl.acm.org/doi/10.1145/3675888.3676049
[4] Aria M. y Cuccurullo C., «bibliometrix: An R-tool for comprehensive science mapping analysis», Journal of Informetrics, vol. 11, n.o 4, pp. 959-975, 2017. [En línea]. Disponible en: https://www.sciencedirect.com/science/article/abs/pii/S1751157717300500
[5] Android Developers Blog, «Google developers blog», 2023. [En línea]. Disponible en: https://developer.android.com/google/play/integrity?hl=es-419
[6] A. Papadopoulos, T. Bäuml, M. Vechev y M. Jaggi, "Android Malware Detection with Unbiased Confidence Guarantees," arXiv preprint arXiv:2312.11559, 2023. [En línea]. Disponible en: https://arxiv.org/abs/2312.11559
[7] Rivera, A., «Análisis de Malware en Android II», Tesis de grado, Universidad Complutense de Madrid, Madrid, 2021. [En línea]. Disponible en: https://eprints.ucm.es/id/eprint/74304/1/RIVERA%20LE%C3%93N%2084977_ALEJANDRO_RIVERA_LEON_Malware_en_Android_II_1398832_1568894276.pdf
[8] Román, A., Luna, V., Sarabia, R., Lechuga, A., Hernández, R., y Rodríguez, N., «Análisis ético de la información en el escándalo Pegasus». [En línea]. Disponible en: https://dialnet.unirioja.es/servlet/articulo?codigo=7237676
[9] Manzil, H. H. R., y Naik, S. M., «DeepMetaDroid: Real-Time Android Malware Detection Using Deep Learning and Metadata Features», Cloud Computing and Data Science, vol. 5, n.º 2, pp. 203–225, 2024. doi: 10.37256/ccds.5220244503. [En línea]. Disponible en: https://ojs.wiserpub.com/index.php/CCDS/article/view/4503
[10] Krzysztoń, M., et al., «BotSense Mobile: Lightweight On-Device Malware Detection in Android», en Sensors, vol. 22, n.º 16, art. 6054, MDPI, 2022. doi: 10.3390/s22166054. [En línea]. Disponible en: https://doi.org/10.3390/s22166054
[11] Anand, S., Mitra, B., Dey, S., Rao, A., Dhar, R., y Vaidya, J., «MALITE: Lightweight Malware Detection and Classification for Constrained Devices», arXiv preprint arXiv:2309.03294, 2023. [En línea]. Disponible en: https://arxiv.org/abs/2309.03294
[12] Qabalin, M., Naser, M., y Alkasassbeh, M., «Detección de spyware en Android mediante el aprendizaje automático: un nuevo conjunto de datos», Sensors, vol. 22, n.o 15, p. 5765, 2022. Disponible en: https://www.mdpi.com/1424-8220/22/15/5765
[13] Montenegro, V., «Análisis comparativo de algoritmos de machine learning para detección de malware en aplicaciones Android», Tesis de grado, Universidad Señor de Sipán, Pimentel, 2022. [En línea]. Disponible en: https://repositorio.uss.edu.pe/bitstream/handle/20.500.12802/10059/Montenegro%20Guerrero%20Victor%20Agustin.pdf?sequence=1&isAllowed=y
[14] Ortega, H., «Smartphones opportunities and risks», vol. 15, n.o 1, pp. 109-140, 2022. Disponible en: https://www.researchgate.net/publication/360702780_SmartphonesOpportunities_and_Risks
[15] Doerfler, P, Chatterjee, R., Orgad, H., Havron, S., y Palmer, J., «The spyware used in intimate partner violence», 2018. [En línea]. Disponible en: https://nyuscholars.nyu.edu/en/publications/the-spyware-used-in-intimate-partner-violence
[16] Pierazzi, F., Mezzour, G., Han, Q., Colajanni, M., y Subrahmanian, V., «Una caracterización basada en datos del spyware moderno de Android», ACM Transactions on Management Information Systems, vol. 11, n.o 1, pp. 1-38, 2020. Disponible en: https://dl.acm.org/doi/fullHtml/10.1145/3382158
[17] Han, Q., Gan, Y., y Gao, Y., «Combinando el aprendizaje automático tradicional y la detección de anomalías en la clasificación de varios conjuntos de datos de malware de Android desequilibrados.», presentado en 7a Conferencia Internacional sobre Máquinas Learning Technologies (ICMLT 2022), Roma, Italia: ACM, mar. 2022, p. 7 páginas. doi: https://doi.org/10.1145/3529399.3529412. [En línea]. Disponible en: https://dblp.org/db/conf/icmlt/icmlt2022.html
[18] Sowndarajan, K. y Binu, B., «Android security issues and solutions», presentado en 2017 International Conference on Innovative Mechanisms for Industry Applications (ICIMIA), 2017. [En línea]. Disponible en: https://www.researchgate.net/publication/318412307_Android_security_issues_and_solutions
[19] J. Zhou, Y. Du, H. Liu, Y. Liu y H. Zhang, "MalPurifier: Enhancing Android Malware Detection with Adversarial Purification," arXiv preprint arXiv:2312.06423, 2023. [En línea]. Disponible en: https://arxiv.org/abs/2312.06423
[20] Viet, N. y Thanh, P., «NADM: Red neuronal para malware de detección de Android», presentado en Noveno Simposio Internacional sobre Tecnología de la Información y la Comunicación (SoICT 2018), Ciudad de Danang, Vietnam: ACM, dic. 2018, p. 7. doi: 10.1145/3287921.3287977. [En línea]. Disponible en: https://dblp.org/rec/conf/soict/DucG18.html
[21] Zhang, R., Chen, X., Wen, S., Zheng, X., y Ding, Y., «Using AI to attack VA: a stealthy spyware against voice assistants in smartphones», [En línea]. Disponible en: https://ieeexplore.ieee.org/document/8861099
[22] PanMan de Wit, J., Bucur, D., y Van Der Ham, J., «Detección dinámica de malware móvil utilizando datos de teléfonos inteligentes y aprendizaje automático», Cifra. Amenaza. Research and Practice, vol. 3, n.o 2, pp. 1-24, 2022. [En línea]. Disponible en: https://dl.acm.org/doi/10.1145/3484246
[23] Hu, Che-Chun y Chen, Yi-Ming, «Análisis dinámico de malware de Android con desidentificación de identificación personal», presentado en 3a Conferencia Internacional sobre Computación y Big Data (ICCBD ’20), Taichung, Taiwán: ACM, ago. 2020, p. 7 páginas. [En línea]. Disponible en: https://dl.acm.org/doi/10.1145/3418688.3418694
Published
Issue
Section
License
Copyright (c) 2025 Mundo FESC Journal
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
