From Deepfake Detection Research to Public Policy: A Survey on Generalization Challenges in Synthetic Media for the Brazilian Electoral Context

Thauan de Souza Tavares da Silva; Diego Addan Gonçalves; David Menotti

doi:10.5753/jis.2026.7969

Authors

Thauan de Souza Tavares da Silva Federal University of Paraná https://orcid.org/0009-0008-9752-6872
Diego Addan Gonçalves Federal University of Paraná https://orcid.org/0000-0003-3355-3966
David Menotti Federal University of Paraná https://orcid.org/0000-0003-2430-2030

DOI:

https://doi.org/10.5753/jis.2026.7969

Keywords:

Public Policy, Digital Governance, Deep-Fake

Abstract

Deepfake detection has advanced rapidly in recent years, yet its practical effectiveness remains limited when models are exposed to real-world conditions that differ from controlled benchmarks. This gap is particularly critical in high-stakes scenarios such as electoral processes, where synthetic media can influence public perception at scale. This paper investigates the generalization limitations of current deepfake detection approaches, with emphasis on their applicability in the Brazilian context. Rather than focusing solely on algorithmic performance, we frame deepfake detection as a socio-technical problem, where issues of trust, interpretability, and user response are central to system effectiveness. Through a critical analysis of existing datasets, evaluation protocols, and detection strategies, we show that current research paradigms often fail to account for distribution shifts, cultural variability, and adversarial adaptation. By bridging detection research with policy-oriented perspectives, this work contributes to a more actionable understanding of how synthetic media challenges can be addressed in Brazil and similar socio-political contexts. Finally, we explicitly derive implications for public policy in the Brazilian electoral context, connecting observed technical limitations to challenges in regulation, platform governance, and the use of automated systems in institutional decision-making.

Downloads

Download data is not yet available.

References

Ação Educativa and Conhecimento Social (2025). Functional literacy indicator (inaf) 2024: Literacy from the analog to the digital world. Technical report, Ação Educativa and Conhecimento Social. URL: [link]; Accessed: 11 August 2026.

Afchar, D., Nozick, V., Yamagishi, J., and Echizen, I. (2018). Mesonet: a compact facial video forgery detection network. In 2018 IEEE International Workshop on Information Forensics and Security (WIFS), pages 1–7. IEEE. DOI: https://doi.org/10.1109/WIFS.2018.8630761.

Al-Naeem, M., Hafizur Rahman, M. M., Banerjee, A., and Sufian, A. (2025). Bsm-dnd: Bias and sensitivity-aware multilingual deepfake news detection using bloom filters and recurrent feature elimination. IEEE Access, 13:163218–163234. DOI: https://doi.org/10.1109/ACCESS.2025.3609831.

Arjovsky, M., Chintala, S., and Bottou, L. (2017). Wasserstein generative adversarial networks. In Proceedings of the 34th International Conference on Machine Learning - Volume 70, ICML'17, page 214–223. JMLR.org. DOI: https://dl.acm.org/doi/10.5555/3305381.3305404.

Bakir, V. and McStay, A. (2018). Fake news and the economy of emotions. Digital Journalism, 6(2):154–175. DOI: https://doi.org/10.1080/21670811.2017.1345645.

Bar-Tal, O., Chefer, H., Tov, O., Herrmann, C., Paiss, R., Zada, S., Ephrat, A., Hur, J., Liu, G., Raj, A., Li, Y., Rubinstein, M., Michaeli, T., Wang, O., Sun, D., Dekel, T., and Mosseri, I. (2024). Lumiere: A space-time diffusion model for video generation. In SIGGRAPH Asia 2024 Conference Papers, SA '24, New York, NY, USA. Association for Computing Machinery. DOI: https://doi.org/10.1145/3680528.3687614.

Battocchio, J., Dell'Anna, S., Montibeller, A., and Boato, G. (2025). Advance fake video detection via vision transformers. In Proceedings of the 2025 ACM Workshop on Information Hiding and Multimedia Security, IH&MMSEC '25, page 1–11, New York, NY, USA. Association for Computing Machinery. DOI: https://doi.org/10.1145/3733102.3733129.

Benevenuto, F. and Melo, P. (2024). Misinformation campaigns through whatsapp and telegram in presidential elections in brazil. Commun. ACM, 67(8):72–77. DOI: https://doi.org/10.1145/3653325.

Brooks, T., Peebles, B., Holmes, C., DePue, W., Guo, Y., Jing, L., Schnurr, D., Scholz, A., Janner, M., Chu, A., et al. (2024). Video generation models as world simulators. Technical report, OpenAI. [link]; Accessed: 11 August 2026.

Brundage, M., Avin, S., Clark, J., Toner, H., Eckersley, P., Garfinkel, B., Dafoe, A., Scharre, P., Zeitzoff, T., Filar, B., Anderson, H., Roff, H., Allen, G. C., Steinhardt, J., Flynn, C., hÉigeartaigh, S. Ó., Beard, S., Belfield, H., Farquhar, S., Lyle, C., Crootof, R., Evans, O., Page, M., Bryson, J., Yampolskiy, R., and Amodei, D. (2018). The malicious use of artificial intelligence: Forecasting, prevention, and mitigation. [link]. Accessed: 11 August 2026.

Centro Regional de Estudos para o Desenvolvimento da Sociedade da Informação (Cetic.br) (2024). Survey on the use of information and communication technologies in brazilian households: Ict households 2024. Technical report, Cetic.br / NIC.br. URL: [link]; Accessed: 11 August 2026.

Chandra, N. A., Lee, H., Murtfeldt, R., Qiu, L., Karmakar, A., Tanumihardja, E., Farhat, K., Caffee, B., Lee, C., Choi, J., Paik, S., Kim, A., and Etzioni, O. (2026). Deepfake-eval-2024: A multi-modal in-the-wild benchmark of deepfakes circulated in 2024. https://doi.org/10.48550/arXiv.2503.02857.

Chollet, F. (2017). Xception: Deep Learning with Depthwise Separable Convolutions. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 1800–1807, Los Alamitos, CA, USA. IEEE Computer Society. DOI: https://doi.org/10.1109/CVPR.2017.195.

Coccomini, D. A., Messina, N., Gennaro, C., and Falchi, F. (2022). Combining efficientnet and vision transformers for video deepfake detection. In Image Analysis and Processing – ICIAP 2022: 21st International Conference, Lecce, Italy, May 23–27, 2022, Proceedings, Part III, page 219–229, Berlin, Heidelberg. Springer-Verlag. DOI: https://doi.org/10.1007/978-3-031-06433-3_19.

Coleti, T. A., Divino, S. B. S., Salgado, A. d. L., Zacarias, R. O., Saraiva, J. d. A. G., Gonçalves, D. A., Morandini, M., and Santos, R. P. d. (2024). Grandihc-br 2025-2035 - gc5 - human-data interaction data literacy and usable privacy. In Proceedings of the XXIII Brazilian Symposium on Human Factors in Computing Systems. DOI: https://doi.org/10.1145/3702038.3702058.

Cunha, Y. M. B. G., Gomes, B. R., Boaro, J. M. C., Moraes, D. d. S., Busson, A. J. G., Duarte, J. C., and Colcher, S. (2024). Learning Self-distilled Features for Facial Deepfake Detection Using Visual Foundation Models: General Results and Demographic Analysis. Journal on Interactive Systems, 15(1):682–694. DOI: https://doi.org/10.5753/jis.2024.4120.

Deressa, D. W., Mareen, H., Lambert, P., Atnafu, S., Akhtar, Z., and Van Wallendael, G. (2025). Genconvit: Deepfake video detection using generative convolutional vision transformer. Applied Sciences, 15(12). DOI: https://doi.org/10.3390/app15126622.

Dhariwal, P. and Nichol, A. (2021). Diffusion models beat gans on image synthesis. In Proceedings of the 35th International Conference on Neural Information Processing Systems, NIPS '21, Red Hook, NY, USA. Curran Associates Inc. DOI: https://dl.acm.org/doi/10.5555/3540261.3540933.

Dolhansky, B., Bitton, J., Pflaum, B., Lu, J., Howes, R., Wang, M., and Ferrer, C. C. (2020). The deepfake detection challenge (dfdc) dataset. https://doi.org/10.48550/arXiv.2006.07397.

Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., and Houlsby, N. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. [link]. Accessed: 11 August 2026.

Garcia, G. L., Afonso, L. C. S., and Papa, J. P. (2022). Fakerecogna: A new brazilian corpus for fake news detection. In Computational Processing of the Portuguese Language: 15th International Conference, PROPOR 2022, Fortaleza, Brazil, March 21–23, 2022, Proceedings, page 57–67, Berlin, Heidelberg. Springer-Verlag. DOI: https://doi.org/10.1007/978-3-030-98305-5_6.

Gillespie, T. (2018). Custodians of the internet: Platforms, content moderation, and the hidden decisions that shape social media. Custodians of the Internet: Platforms, Content Moderation, and the Hidden Decisions That Shape Social Media, pages 1–288. DOI: https://doi.org/10.12987/9780300235029.

Goodfellow, I. J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative adversarial nets. In Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 2, NIPS'14, page 2672–2680, Cambridge, MA, USA. MIT Press. DOI: https://dl.acm.org/doi/10.5555/2969033.2969125.

Gorwa, R., Binns, R., and Katzenbach, C. (2020). Algorithmic content moderation: Technical and political challenges in the automation of platform governance. Big Data & Society, 7(1):2053951719897945. DOI: https://doi.org/10.1177/2053951719897945.

Ho, J., Jain, A., and Abbeel, P. (2020). Denoising diffusion probabilistic models. In Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS '20, Red Hook, NY, USA. Curran Associates Inc. DOI: https://dl.acm.org/doi/abs/10.5555/3495724.3496298.

Karras, T., Aittala, M., Laine, S., Härkönen, E., Hellsten, J., Lehtinen, J., and Aila, T. (2021a). Alias-free generative adversarial networks. In Proceedings of the 35th International Conference on Neural Information Processing Systems, NIPS '21, Red Hook, NY, USA. Curran Associates Inc. DOI: https://dl.acm.org/doi/10.5555/3540261.3540327.

Karras, T., Laine, S., and Aila, T. (2021b). A style-based generator architecture for generative adversarial networks. IEEE Trans. Pattern Anal. Mach. Intell., 43(12):4217–4228. DOI: https://doi.org/10.1109/TPAMI.2020.2970919.

Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., and Aila, T. (2020). Analyzing and Improving the Image Quality of StyleGAN. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 8107–8116, Los Alamitos, CA, USA. IEEE Computer Society. DOI: https://doi.org/10.1109/CVPR42600.2020.00813.

Korshunova, I., Shi, W., Dambre, J., and Theis, L. (2017). Fast face-swap using convolutional neural networks. In 2017 IEEE International Conference on Computer Vision (ICCV), pages 3697–3705. DOI: https://doi.org/10.1109/ICCV.2017.397.

Li, Y. and Lyu, S. (2019). Exposing deepfake videos by detecting face warping artifacts. https://doi.org/10.48550/arXiv.1811.00656.

Li, Y., Yang, X., Sun, P., Qi, H., and Lyu, S. (2020). Celeb-df: A large-scale challenging dataset for deepfake forensics. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 3204–3213. DOI: https://doi.org/10.1109/CVPR42600.2020.00327.

Mirsky, Y. and Lee, W. (2021). The creation and detection of deepfakes: A survey. ACM Comput. Surv., 54(1). DOI: https://doi.org/10.1145/3425780.

Newman, N., Fletcher, R., Robertson, C. T., Ross Arguedas, A., and Nielsen, R. K. (2024). Reuters institute digital news report 2024: Brazil. Technical report, Reuters Institute for the Study of Journalism, University of Oxford. [link]; Accessed: 11 August 2026.

Nightingale, S. J. and Farid, H. (2022). Ai-synthesized faces are indistinguishable from real faces and more trustworthy. Proceedings of the National Academy of Sciences, 119(8):e2120481119. DOI: https://doi.org/10.1073/pnas.2120481119.

Odena, A., Dumoulin, V., and Olah, C. (2016). Deconvolution and checkerboard artifacts. Distill, 1(10):e3. DOI: https://doi.org/10.23915/distill.00003.

Peng, N. and Zhao, T.-F. (2025). Unveiling risk evolution mechanisms driven by deepfake technologies. In 2025 12th International Conference on Machine Intelligence Theory and Applications (MiTA), pages 1–8. DOI: https://doi.org/10.1109/MiTA66017.2025.11100255.

Pereira, R., Darin, T., and Silveira, M. S. (2024). Grandihc-br: Grand research challenges in human-computer interaction in brazil for 2025-2035. In Proceedings of the XXIII Brazilian Symposium on Human Factors in Computing Systems. Association for Computing Machinery. DOI: https://dl.acm.org/doi/10.1145/3702038.3702061.

Puska, A. A., Baroni, L. A., and Pereira, R. (2024). Decoding the sociotechnical dimensions of digital misinformation: A comprehensive literature review. https://doi.org/10.48550/arXiv.2406.11853.

Radford, A., Metz, L., and Chintala, S. (2016). Unsupervised representation learning with deep convolutional generative adversarial networks. [link]. Accessed: 11 August 2026.

Reis, J. C. S., Melo, P., Garimella, K., Almeida, J. M., Eckles, D., and Benevenuto, F. (2020). A dataset of fact-checked images shared on WhatsApp during the Brazilian and Indian elections. In Proceedings of the 14th International AAAI Conference on Web and Social Media, ICWSM 2020, pages 903–908. DOI: https://doi.org/10.1609/icwsm.v14i1.7356.

Rombach, R., Blattmann, A., Lorenz, D., Esser, P., and Ommer, B. (2022). High-Resolution Image Synthesis with Latent Diffusion Models. In 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 10674–10685, Los Alamitos, CA, USA. IEEE Computer Society. DOI: https://doi.org/10.1109/CVPR52688.2022.01042.

Rossler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., and Niessner, M. (2019). FaceForensics++: Learning to Detect Manipulated Facial Images. In 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pages 1–11, Los Alamitos, CA, USA. IEEE Computer Society. DOI: https://doi.org/10.1109/ICCV.2019.00009.

Runway Research (2023). Runway gen-3: Text-to-video generation model. [link]. Online; accessed 11 August 2026.

Sagar, A. S. M. S., Bennamoun, M., Boussaid, F., Sharif, N., Xu, L., Sahmoud, S., and Kishk, A. (2026). Fact or fake? assessing the role of deepfake detectors in multimodal misinformation detection. IEEE Access, 14:86992–87011. DOI: https://doi.org/10.1109/ACCESS.2026.3686437.

Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., and Chen, X. (2016). Improved techniques for training gans. In Proceedings of the 30th International Conference on Neural Information Processing Systems, NIPS'16, page 2234–2242, Red Hook, NY, USA. Curran Associates Inc. DOI: https://dl.acm.org/doi/abs/10.5555/3157096.3157346.

Shoaib, M. R., Wang, Z., Ahvanooey, M. T., and Zhao, J. (2023). Deepfakes, misinformation, and disinformation in the era of frontier ai, generative ai, and large ai models. In 2023 International Conference on Computer and Applications (ICCA), pages 1–7. DOI: https://doi.org/10.1109/ICCA59364.2023.10401723.

Sohl-Dickstein, J., Weiss, E. A., Maheswaranathan, N., and Ganguli, S. (2015). Deep unsupervised learning using nonequilibrium thermodynamics. In Proceedings of the 32nd International Conference on Machine Learning - Volume 37, ICML'15, page 2256–2265. JMLR.org. DOI: https://dl.acm.org/doi/10.5555/3045118.3045358.

Tan, C., Liu, H., Zhao, Y., Wei, S., Gu, G., Liu, P., and Wei, Y. (2024). Rethinking the up-sampling operations in cnn-based generative network for generalizable deepfake detection. In 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 28130–28139. DOI: https://doi.org/10.1109/CVPR52733.2024.02657.

Thies, J., Zollhöfer, M., Stamminger, M., Theobalt, C., and Nießner, M. (2016). Face2face: Real-time face capture and reenactment of rgb videos. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 2387–2395. DOI: https://doi.org/10.1109/CVPR.2016.262.

Tolosana, R., Vera-Rodriguez, R., Fierrez, J., Morales, A., and Ortega-Garcia, J. (2020). Deepfakes and beyond: A survey of face manipulation and fake detection. Information Fusion, 64:131–148. DOI: https://doi.org/10.1016/j.inffus.2020.06.014.

Vaccari, C. and Chadwick, A. (2020). Deepfakes and disinformation: Exploring the impact of synthetic political video on deception, uncertainty, and trust in news. Social Media + Society, 6(1):2056305120903408. DOI: https://doi.org/10.1177/2056305120903408.

Veale, M., Van Kleek, M., and Binns, R. (2018). Fairness and accountability design needs for algorithmic support in high-stakes public sector decision-making. In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems, CHI '18, pages 1–14, New York, NY, USA. Association for Computing Machinery. DOI: https://dl.acm.org/doi/10.1145/3173574.3174014.

Villela, H. F., Corrêa, F., Ribeiro, J. S. d. A. N., Rabelo, A., and Carvalho, D. B. F. (2023). Fake news detection: a systematic literature review of machine learning algorithms and datasets. Journal on Interactive Systems, 14(1):47–58. DOI: https://doi.org/10.5753/jis.2023.3020.

Wang, S.-Y., Wang, O., Zhang, R., Owens, A., and Efros, A. A. (2020). Cnn-generated images are surprisingly easy to spot. . . for now. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 8692–8701. DOI: https://doi.org/10.1109/CVPR42600.2020.00872.

Xu, Y., Terhörst, P., Pedersen, M., and Raja, K. (2024). Analyzing fairness in deepfake detection with massively annotated databases. IEEE Transactions on Technology and Society, 5(1):93–106. DOI: https://doi.org/10.1109/TTS.2024.3365421.