Deepfakes: Revisión sistemática de tecnologías, impacto y estrategias de detección
DOI:
https://doi.org/10.36825/RITI.13.29.003Palabras clave:
Deepfakes, Inteligencia Artificial, Deep Learning, Desinformación, ÉticaResumen
Este articulo tiene por objetivo proporcionar una visión detallada y crítica del estado del arte acerca de los deepfakes a nivel global, identificando las principales tecnologías utilizadas, sus efectos en diferentes sectores de la sociedad y las estrategias efectivas para su detección. A partir de un enfoque cualitativo de nivel exploratorio para llevar a cabo esta revisión sistemática de la literatura, se analizaron 43 artículos de los últimos cinco años de diferentes países. Los principales hallazgos fueron las coincidencias con las investigaciones que proponen diversos modelos de detección; además de trabajos que hablan acerca de la desconfianza de la sociedad por la legitimidad de la información, lo cual fue un tema frecuente. Sin embargo, hubo publicaciones que resaltan la diversidad de enfoques y la necesidad de abordar el fenómeno de los deepfakes desde múltiples perspectivas. Este trabajo aporta una comprensión integral del problema de los deepfakes, conectando hallazgos técnicos, sociales y éticos, y subrayando la importancia de abordarlo desde una perspectiva global.
Citas
Malik, A., Kuribayashi, M., Abdullahi, S., Khan, A. (2022). Deepfake detection for human face images and videos: a survey. IEEE Access, 10, 18757-18775. https://doi.org/10.1109/ACCESS.2022.3151186
Kirchengast, T. (2020). Deepfakes and image manipulation: criminalisation and control. Information & Communications Technology Law, 29 (3), 308-323. https://doi.org/10.1080/13600834.2020.1794615
Bañuelos, J., Abbruzzese, M. (2023). From deepfake to deeptruth: toward a technological resignification with social and activist uses. En M. Cebral-Loureda, E. G. Rincón-Flores, G. Sanchez-Ante (Eds.), What AI Can Do: Strengths and Limitations of Artificial Intelligence (pp. 75-92). Taylor & Francis Group. https://doi.org/10.1201/b23345
Hao, K. (2020). El año que los deepfakes salieron del lado oscuro y se masificaron. MIT Technology Review. https://www.technologyreview.es/s/13049/el-ano-que-los-deepfakes-salieron-del-lado-oscuro-y-se-masificaron
Songja, R., Promboot, I., Haetanurak, B., Kerdvibulvech, C. (2023). Deepfake AI images: should deepfakes be banned in Thailand?. AI and Ethics, 4, 1519-1531. https://doi.org/10.1007/s43681-023-00350-0
De Ruiter, A. (2021). The distinct wrong of deepfakes. Philosophy & Technology, 34 (4), 1311-1332. https://doi.org/10.1007/s13347-021-00459-2
Maniyal, V., Kumar, V. (2024). Unveiling the Deepfake Dilemma: Framework, Classification, and Future Trajectories. IT Professional, 26 (2), 32-38. https://doi.org/10.1109/MITP.2024.3369948
Ramos-Zaga, F. (2024). Deepfake: Análisis de sus implicancias tecnológicas y jurídicas en la era de la Inteligencia Artificial. Derecho Global. Estudios sobre Derecho y Justicia, 9 (27), 359-387. https://doi.org/10.32870/dgedj.v9i27.754
Vinogradova, E. A. (2023). The malicious use of political deepfakes and attempts to neutralize them in Latin America. Latinskaya Amerika, (5), 35-48. https://doi.org/10.31857/S0044748X0025404-3
De Rancourt-Raymond, A., Smaili, N. (2023). The unethical use of deepfakes. Journal of Financial Crime, 30 (4), 1066-1077. https://doi.org/10.1108/JFC-04-2022-0090
Gregory, S. (2023). Fortify the truth: How to defend human rights in an age of deepfakes and generative AI. Journal of Human Rights Practice, 15 (3), 702-714. https://doi.org/10.1093/jhuman/huad035
Catota, F. E., Morgan, M. G., Sicker, D. C. (2019). Cybersecurity education in a developing nation: The Ecuadorian environment. Journal of Cybersecurity, 5 (1), 1-19. https://doi.org/10.1093/cybsec/tyz001
Seow, J. W., Lim, M. K., Phan, R. C., Liu, J. K. (2022). A comprehensive overview of Deepfake: Generation, detection, datasets, and opportunities. Neurocomputing, 513, 351-371. https://doi.org/10.1016/j.neucom.2022.09.135
Gambín, Á. F., Yazidi, A., Vasilakos, A., Haugerud, H., Djenouri, Y. (2024). Deepfakes: current and future trends. Artificial Intelligence Review, 57 (64), 1-32. https://doi.org/10.1007/s10462-023-10679-x
Heidari, A., Jafari Navimipour, N., Dag, H., Unal, M. (2024). Deepfake detection using deep learning methods: A systematic and comprehensive review. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 14 (2), 1-45. https://doi.org/10.1002/widm.1520
Bañuelos Capistrán, J. (2022). Evolución del Deepfake: campos semánticos y géneros discursivos 2017-2021. Revista ICONO 14. Revista de Comunicación y Tecnologías Emergentes, 20 (1), 1-21. https://doi.org/10.7195/ri14.v20i1.1773
Amerini, I., Barni, M., Battiato, S., Bestagini, P., Boato, G., Bonaventura, T. S., Bruni, V., Caldelli, R., De Natale, F., De Nicola, R., Guarnera, L., Mandelli, S., Marcialis, G. L., Micheletto, M., Montibeller, A., Orrù, G., Ortis, A., Perazzo, P., Puglisi, G., Salvi, D., Tubaro, S., Tonti, C. M., Villari, M., Vitulano, D. (2024). Deepfake Media Forensics: State of the Art and Challenges Ahead. arXiv preprint. https://arxiv.org/pdf/2408.00388
Altuncu, E., Franqueira, V. N. L., Li, S. (2024). Deepfake: definitions, performance metrics and standards, datasets, and a meta-review. Frontiers in Big Data, 7, 1-23. https://doi.org/10.3389/fdata.2024.1400024
Domenteanu, A., Tataru, G. C., Craciun, L., Molanescu, A. G., Cotfas, L. A., Delcea, C. (2024). Living in the Age of Deepfakes: A Bibliometric Exploration of Trends, Challenges, and Detection Approaches. Information, 15 (9), 1-31. https://doi.org/10.3390/info15090525
Le, B. M., Kim, J., Tariq, S., Moore, K., Abuadbba, A., Woo, S. S. (2024). Sok: Facial deepfake detectors. arXiv preprint. https://doi.org/10.48550/arXiv.2401.04364
Romero Moreno, F. (2024). Generative AI and deepfakes: a human rights approach to tackling harmful content. International Review of Law, Computers & Technology, 38 (3), 297–326. https://doi.org/10.1080/13600869.2024.2324540
Jacobsen, B. N., Simpsons, J. (2022) The tensions of deepfakes. Information, communication & society, 27 (6), 1095-1109. https://doi.org/10.1080/1369118X.2023.2234980
Ramon, M., Vowels, M., Groh, M. (2024). Deepfake Detection in Super-Recognizers and Police Officers, IEEE Security & Privacy, 22 (3), pp. 68-76. https://doi.org/10.1109/MSEC.2024.3371030
Wang, T., Liao, X., Pui Chow, K., Lin, X., Wang, Y. (2024). Deepfake Detection: A Comprehensive Survey from the Reliability Perspective. ACM Computing Surveys, 57 (3), 1-35. https://doi.org/10.1145/3699710
Argallero Fernández, P. (2024). Reconocimiento de DeepFakes. [Tesis de Licenciatura]. Universidad de Oviedo, España. https://hdl.handle.net/10651/74464
Barrientos-Báez, A., Piñeiro Otero, M. T., Porto Renó, D. (2024). Imágenes falsas, efectos reales. Deepfakes como manifestaciones de la violencia política de género. Revista Latina De Comunicación Social, (82), 1–30. https://doi.org/10.4185/rlcs-2024-2278
Alanazi, S., Asif, S. (2024). Exploring deepfake technology: creation, consequences and countermeasures. Human-Intelligent Systems Integration, 6, 49-60. https://doi.org/10.1007/s42454-024-00054-8
Pawelec, M. (2024). Decent deepfakes? (2024). Professional deepfake developers’ ethical considerations and their governance potential. AI and Ethics, 1-26. https://doi.org/10.1007/s43681-024-00542-2
Hameleers, M. (2024). Cheap Versus Deep Manipulation: The Effects of Cheapfakes Versus Deepfakes in a Political Setting. International Journal of Public Opinion Research, 36 (1), 1-9. https://doi.org/10.1093/ijpor/edae004
Agarwal, A., Ratha, N. (2024). Deepfake Catcher: Can a Simple Fusion be Effective and Outperform Complex DNNs? IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA. https://doi.org/10.1109/CVPRW63382.2024.00383
Astrid, M., Ghorbel, E., Aouada, D. (2024). Detecting Audio-Visual Deepfakes with Fine-Grained Inconsistencies. arXiv preprint. https://doi.org/10.48550/arXiv.2408.06753
Nadimpalli, A. V., Rattani, A. (2024). Social Media Authentication and Combating Deepfakes using Semi-fragile Invisible Image Watermarking. Digital Threats: Research and Practice, 5 (4), 1-30. https://doi.org/10.1145/3700146
Kingra, S., Aggarwal, N., Kaur, N. (2024). SFormer: An end-to-end spatio-temporal transformer architecture for deepfake detection. Forensic Science International: Digital Investigation, 51. https://doi.org/10.1016/j.fsidi.2024.301817
Samuel-Okon, A. D., Akinola, O. I., Olaniyi, O. O., Olateju, O. O., Ajayi, S. A. (2024). Assessing the Effectiveness of Network Security Tools in Mitigating the Impact of Deepfakes AI on Public Trust in Media. Archives of Current Research International, 24 (6), 355-375. https://doi.org/10.9734/acri/2024/v24i6794
Zang, Y., Zhang, Y., Heydari, M., Duan, Z. (2024). SingFake: Singing Voice Deepfake Detection. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Seoul, Republic of Korea https://doi.org/10.1109/ICASSP48485.2024.10448184
Datta, S. K., Jia, S., Lyu, S. (2024). Exposing Lip-syncing Deepfakes from Mouth Inconsistencies. arXiv preprint. https://doi.org/10.48550/arXiv.2401.10113
Sun, P., Qi, H., Li, Y., Lyu, S. (2024). FakeTracer: Catching Face-swap DeepFakes via Implanting Traces in Training. IEEE Transactions on Emerging Topics in Computing, 1-12. https://doi.ieeecomputersociety.org/10.1109/TETC.2024.3386960
Nguyen, D., Mejri, N., Singh, I. P., Kuleshova, P., Astrid, M., Kacem, A. (2024). LAA-Net: Localized Artifact Attention Network for Quality-Agnostic and Generalizable Deepfake Detection. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, WA, USA. https://doi.org/10.1109/CVPR52733.2024.01647
Qu, Z., Xi, Z., Lu, W., Luo, X., Wang, Q., Li, B. (2024). DF-RAP: A Robust Adversarial Perturbation for Defending against Deepfakes in Real-world Social Network Scenarios. IEEE Transactions on Information Forensics and Security, 19, 3943-3957. https://doi.org/10.1109/tifs.2024.3372803
Pandey, M., Singh, S., Malik, A., Kumar, R. (2024). Detecting low-resolution deepfakes: An exploration of machine learning techniques. Multimedia Tools and Applications, 83, 66283–66298. https://doi.org/10.1007/s11042-024-18235-7
Krishnan, K. S., Krishnan, K. S. (2023). MFAAN: Unveiling Audio Deepfakes with a Multi-Feature Authenticity Network. 9th International Conference on Signal Processing and Communication (ICSC). Noida, India. https://doi.org/10.1109/icsc60394.2023.10441405
Hou, Y., Guo, Q., Huang, Y., Xie, X., Ma, L., Zhao, J. (2023). Evading deepfake detectors via adversarial statistical consistency. IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver, BC, Canada. https://doi.org/10.1109/CVPR52729.2023.01181
Li, B., Sun, J., Poskitt, C. M., Wang, X. (2023). How generalizable are deepfake detectors? An empirical study. arXiv preprint. https://doi.org/10.48550/arXiv.2308.04177
Doss, C., Mondschein, J., Shu, D., Wolfson, T., Kopecky, D., Fitton-Kane, V. A., Bush, L., Tucker, C. (2023). Deepfakes and scientific knowledge dissemination. Scientirfic Reports, 13, 1-12. https://doi.org/10.1038/s41598-023-39944-3
Bray, S. D., Johnson, S. D., Kleinberg, B. (2023). Testing human ability to detect ‘deepfake’ images of human faces. Journal of Cybersecurity, 9 (1), 1-18. https://doi.org/10.1093/cybsec/tyad011
Leone, M. (2022). L’idéologie sémiotique des deepfakes. Interfaces numériques, 11 (2), 1-16. https://doi.org/10.25965/interfaces-numeriques.4847
Atamna, M. M., Tkachenko, I., Miguet, S. (2022). Détection de Deepfakes par Réseaux de Convolution: Performances et Limites Actuelles. XXVIIIème Colloque Francophone de Traitement du Signal et des Images. Nancy, Francia. https://hal.science/hal-03769784/document
Pignier, N. (2022). L’énonciation à l’épreuve de l’«IA». Qu’est-ce-qu’énoncer veut dire? Interfaces numériques, 11 (2), 1-17. https://doi.org/10.25965/interfaces-numeriques.4897
Nelson, J. (2022). Fake news et deepfakes: Une approche cyberpsychologique. Interfaces numériques, 11 (2), 1-13. https://doi.org/10.25965/interfaces-numeriques.4830
Caliandro, S. (2022). Fake Art, entre le contrefait et le contrefactuel. Interfaces numériques, 11 (2). 1-14. https://doi.org/10.25965/interfaces-numeriques.4889
Lloveria, V. (2022). Le deepfake et son métadiscours: l’art de montrer que l’on ment. Interfaces numériques, 11 (2). 1-22. https://doi.org/10.25965/interfaces-numeriques.4876
Fabre, M. (2022). Urdoxa, le deepfake d’information comme usage tactique du vague La sémiotique au défi de l’évidence. Interfaces numériques, 11 (2). 1-15. https://dx.doi.org/10.25965/interfaces-numeriques.4863
Dondero, M. G. (2022). Du portrait pictural aux deepfakes: le visage en tant que totalité. Interfaces numériques, 11 (2), 1-19. https://doi.org/10.25965/interfaces-numeriques.4855
Narayan, K., Agarwal, H., Thakral, K., Mittal, S., Vatsa, M., Singh, R. (2022). DeePhy: On Deepfake Phylogeny. IEEE International Joint Conference on Biometrics (IJCB). Abu Dhabi, United Arab Emirates. https://doi.org/10.1109/IJCB54206.2022.10007968
Appel, M., Prietzel, F. (2023). The detection of political deepfakes. Journal of Computer-Mediated Communication, 27 (4), 1-13. https://doi.org/10.1093/jcmc/zmac008
Helmus, T. C. (2022). Artificial Intelligence, Deepfakes, and Disinformation. http://www.jstor.org/stable/resrep42027
Taeb, M., Chi, H. (2022). Comparison of Deepfake Detection Techniques through Deep Learning. Journal of Cybersecurity and Privacy, 2 (1), 89-106. https://doi.org/10.3390/jcp2010007
Eberl, A., Kühn, J., Wolbring, T. (2022). Using deepfakes for experiments in the social sciences-A pilot study. Frontiers in Sociology,7, 1-11. https://doi.org/10.3389/fsoc.2022.907199
Zhou, Y., Lim, S.-N. (2021). Joint Audio-Visual Deepfake Detection. IEEE/CVF International Conference on Computer Vision (ICCV). Montreal, QC, Canada. https://doi.org/10.1109/ICCV48922.2021.01453
Ramachandran, S., Nadimpalli, A. V., Rattani, A. (2021) An Experimental Evaluation on Deepfake Detection using Deep Face Recognition. International Carnahan Conference on Security Technology (ICCST). Hatfield, United Kingdom. https://doi.org/10.1109/ICCST49569.2021.9717407
Zendran, M., Rusiecki, A. (2021). Swapping face images with generative neural networks for deepfake technology–experimental study. Procedia computer science, 192, 834-843. https://doi.org/10.1016/j.procs.2021.08.086
Hazeu-Gonzalez, M. (2021). Sistemas cognitivos artificiales para la detección de deepfakes usando datos audio-visuales [Master's Thesis]. Universidad Internacional de la Rioja (UNIR). https://reunir.unir.net/handle/123456789/12080
Grandío Rodríguez, S. (2021). Desarrollo de una aplicación de creación de deepfakes en tiempo real para el uso del agente encubierto informático. Revista de Investigación CUGC, (8). https://dialnet.unirioja.es/servlet/articulo?codigo=9427400
Korshunov, P., Marcel, S. (2020). Deepfake detection: humans vs. machines. arXiv preprint https://doi.org/10.48550/arXiv.2009.03155
Descargas
Publicado
Cómo citar
Número
Sección
Licencia
Derechos de autor 2025 Revista de Investigación en Tecnologías de la Información
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial 4.0.
Esta revista proporciona un acceso abierto a su contenido, basado en el principio de que ofrecer al público un acceso libre a las investigaciones ayuda a un mayor intercambio global del conocimiento.
El texto publicado en la Revista de Investigación en Tecnologías de la Información (RITI) se distribuye bajo la licencia Creative Commons (CC BY-NC
), que permite a terceros utilizar lo publicado citando a los autores del trabajo y a RITI, pero sin hacer uso del material con propósitos comerciales.
