Transferência de aprendizado em redes neurais convolucionais para detecção de deepfakes faciais.
| dc.contributor.advisor | Costa, Elloá Barreto Guedes da | |
| dc.contributor.advisor-lattes | http://lattes.cnpq.br/6466781778573760 | |
| dc.contributor.author | Silva, Liliana Oliveira Da | |
| dc.contributor.author-lattes | http://lattes.cnpq.br/1067041052566856 | |
| dc.contributor.referee1 | Costa, Elloá Barreto Guedes da | |
| dc.contributor.referee1Lattes | http://lattes.cnpq.br/6466781778573760 | |
| dc.contributor.referee2 | Melo, Aurea Hileia da Silva | |
| dc.contributor.referee2Lattes | http://lattes.cnpq.br/0243106634406881 | |
| dc.contributor.referee3 | Tamayo, Sergio Cleger | |
| dc.contributor.referee3Lattes | http://lattes.cnpq.br/1042990074656681 | |
| dc.date.accessioned | 2026-09-14T18:33:06Z | |
| dc.date.issued | 2026-09-19 | |
| dc.description.abstract | The proliferation of highly realistic synthetic media (deepfakes) demands robust detection methods. This study investigates the effectiveness of Convolutional Neural Networks (VGG16, ResNet-152, and Inception-v3) in identifying facial deepfakes using Transfer Learning. The methodology encompassed feature extraction and fine-tuning experiments on a realistic dataset from the literature. Internal results highlighted the ResNet-152 architecture as the bestperforming model, achieving over 99% accuracy after fine-tuning. However, external validation tests on unseen images revealed a drop in network performance, emphasizing the critical generalization challenge models face against novel synthesis methods. We conclude that while the evaluated architectures are highly effective within known domains, it is essential to develop strategies that enhance their generalization capacity to keep pace with the rapid evolution of generative artifical intelligence technologies. | |
| dc.description.resumo | A proliferação de mídias sintéticas altamente verossímeis (deepfakes) exige métodos robustos de detecção. Este trabalho investiga a eficácia de Redes Neurais Convolucionais (VGG16, ResNet-152 e Inception-v3) na identificação de deepfakes faciais, empregando Transferência de Aprendizado. A metodologia englobou experimentos de extração de características e ajuste fino (fine-tuning) em uma base de dados realista da literatura. Os resultados internos evidenciaram a arquitetura ResNet-152 com o melhor desempenho, alcançando acurácia superior a 99% após o ajuste fino. Contudo, testes de validação externa em imagens inéditas revelaram uma queda de desempenho das redes, destacando o crítico desafio de generalização dos modelos frente a novos métodos de síntese. Conclui-se que, embora as arquiteturas avaliadas sejam altamente eficazes no domínio conhecido, é imprescindível desenvolver estratégias que ampliem a capacidade de generalização das redes para acompanhar a rápida evolução das tecnologias de Inteligência Artificial Generativa. | |
| dc.identifier.citation | SILVA, Liliana Oliveira Da. Transferência de aprendizado em redes neurais convolucionais para detecção de deepfakes faciais, Manaus, 2026. 61 f. TCC- (Graduação em Engenharia de Computação) – Universidade do Estado do Amazonas. Escola Superior de Tecnologia. | |
| dc.identifier.uri | https://ri.uea.edu.br/handle/riuea/8631 | |
| dc.language.iso | pt | |
| dc.publisher | Universidade do Estado do Amazonas | |
| dc.publisher.initials | UEA | |
| dc.relation.references | AYDIN, Ö.; KARAARSLAN, E. Is chatgpt leading generative ai? what is beyond expectations? Academic Platform Journal of Engineering and Smart Systems, Akademik Perspektif Derneği, v. 11, n. 3, p. 118–134, 2023. BISHOP, C. M. Neural networks and their applications. Review of scientific instruments, American Institute of Physics, v. 65, n. 6, p. 1803–1832, 1994. BISHOP, C. M. Neural networks for pattern recognition. [S.l.]: Oxford university press, 1995. BRAGA, A. d. P.; LUDERMIR, T. B.; CARVALHO, A. C. P. d. L. F. d. Redes neurais artificiais: teoria e aplicações. 2000. BRASIL. Ministério da Ciência, Tecnologia e Inovação. Plano Brasileiro de Inteligência Artificial (PBIA) 2024–2028: Inteligência Artificial para o Bem de Todos. Brasília, DF, 2024. Disponível em: <https://www.gov.br/mcti/pt-br/acompanhe-o-mcti/pbia/pbia-documento-oficial.pdf>. Acesso em: 26 mai. 2026. BRYNJOLFSSON, E.; LI, D.; RAYMOND, L. Generative ai at work. The Quarterly Journal of Economics, Oxford University Press, v. 140, n. 2, p. 889–942, 2025. CHEN, Y. et al. X2-dfd: A framework for explainable and extendable deepfake detection. Advances in Neural Information Processing Systems, v. 38, p. 83792–83839, 2026. CHENG, H. et al. Diffusion facial forgery detection. In: Proceedings of the 32nd ACM international conference on multimedia. [S.l.: s.n.], 2024. p. 5939–5948. CHOLLET, F. Deep Learning with Python. 2. ed. Estados Unidos: Manning Publications, 2021. EVERINGHAM, M. et al. The pascal visual object classes challenge: A retrospective. International journal of computer vision, Springer, v. 111, n. 1, p. 98–136, 2015. GOODFELLOW, I. et al. Deep learning. [S.l.]: MIT press Cambridge, 2016. v. 1. GRIFFIN, G.; HOLUB, A.; PERONA, P. Caltech-256 object category dataset. 2007. HAYKIN, S. Neural Networks and Learning Machines. 3. ed. Estados Unidos: Pearson Prentice-Hall, 2009. HE, K. et al. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. [S.l.: s.n.], 2016. p. 770–778. JAIDKA, K. et al. Misinformation, disinformation, and generative ai: Implications for perception and policy. Digital Government: Research and Practice, ACM New York, NY, v. 6, n. 1, p. 1–15, 2025. JORDAN, M. I.; MITCHELL, T. M. Machine learning: Trends, perspectives, and prospects. Science, American Association for the Advancement of Science, v. 349, n. 6245, p. 255–260, 2015. KARRAS, T. et al. Alias-free generative adversarial networks. Advances in neural information processing systems, v. 34, p. 852–863, 2021. KHAN, S. et al. A Guide to Convolutional Neural Networks for Computer Vision. 1a. ed. San Rafael, California, USA: Morgan & Claypool, 2018. (Synthesis Lectures on Computer Vision). KRIZHEVSKY, A.; SUTSKEVER, I.; HINTON, G. E. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, v. 25, 2012. LIN, M.; CHEN, Q.; YAN, S. Network in network. arXiv preprint arXiv:1312.4400, 2013. LIN, T.-Y. et al. Microsoft coco: Common objects in context. In: SPRINGER. European conference on computer vision. [S.l.], 2014. p. 740–755. MA, L. et al. From specificity to generality: Revisiting generalizable artifacts in detecting face deepfakes. Advances in Neural Information Processing Systems, v. 38, p. 69306–69344, 2026. MCCULLOCH, W. S.; PITTS, W. A logical calculus of the ideas immanent in nervous activity. The bulletin of mathematical biophysics, Springer, v. 5, n. 4, p. 115–133, 1943. MIRSKY, Y.; LEE, W. The creation and detection of deepfakes: A survey. ACM computing surveys (CSUR), ACM New York, NY, USA, v. 54, n. 1, p. 1–41, 2021. MITCHELL, T. Machine Learning. McGraw-Hill Education, 1997. (McGraw-Hill international editions - computer science series). ISBN 9780070428072. Disponível em:<https://books.google.com.br/books?id=xOGAngEACAAJ>. NAFFI, N. Deepfakes and the crisis of knowing. 2025. Disponível em: <https://www.unesco. org/en/articles/deepfakes-and-crisis-knowing>. PAN, S. J.; YANG, Q. A survey on transfer learning. IEEE Transactions on knowledge and data engineering, IEEE, v. 22, n. 10, p. 1345–1359, 2009. PARK, S.; NAN, X. Generative ai and misinformation: a scoping review of the role of generative ai in the generation, detection, mitigation, and impact of misinformation. AI & SOCIETY, Springer, p. 1–15, 2025. PEEBLES, W.; XIE, S. Scalable diffusion models with transformers. In: Proceedings of the IEEE/CVF international conference on computer vision. [S.l.: s.n.], 2023. p. 4195–4205. RANA, M. S. et al. Deepfake detection: A systematic literature review. IEEE access, IEEE, v. 10, p. 25494–25513, 2022. RICH, E.; KNIGHT, K. et al. Inteligencia artificial. Madrid: McGraw-Hill„ 1994. ROSSLER, A. et al. Faceforensics++: Learning to detect manipulated facial images. In: Proceedings of the IEEE/CVF international conference on computer vision. [S.l.: s.n.], 2019. p. 1–11. RUMELHART, D. E.; HINTON, G. E.; WILLIAMS, R. J. Learning representations by back-propagating errors. nature, Nature Publishing Group UK London, v. 323, n. 6088, p.533–536, 1986. RUSSAKOVSKY, O. et al. Imagenet large scale visual recognition challenge. International journal of computer vision, Springer, v. 115, n. 3, p. 211–252, 2015. RUSSELL, S.; NORVIG, P. Artificial Intelligence – A Modern Approach. 3. ed. Nova Jersey: Pearson, 2016. SANCHES, D.; MENEZES, P. Conectividade significativa e desinformação: quais são as competências e os saberes necessários na era da IA generativa? 2025. In: NIC.br. Pesquisa sobre o uso das tecnologias de informação e comunicação nos domicílios brasileiros: TIC Domicílios 2024. São Paulo: CGI.br, pp. 93–101. Capítulo de Livro. Acesso em: 18 jan. 2026. SARKAR, D.; BALI, R.; GHOSH, T. Hands-On Transfer Learning with Python: Implement advanced deep learning and neural network models using TensorFlow and Keras. [S.l.]: Packt Publishing Ltd, 2018. SIMONYAN, K.; ZISSERMAN, A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014. SZEGEDY, C. et al. Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition. [S.l.: s.n.], 2015. p. 1–9. SZEGEDY, C. et al. Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition. [S.l.: s.n.], 2016. p.2818–2826. WANG, G. et al. Fsfm: A generalizable face security foundation model via self-supervised facial representation learning. In: Proceedings of the Computer Vision and Pattern Recognition Conference. [S.l.: s.n.], 2025. p. 24364–24376. WIDROW, B.; HOFF, M. E. Adaptive switching circuits. In: Neurocomputing: foundations of research. [S.l.: s.n.], 1988. p. 123–134. World Economic Forum. The Global Risks Report 2025. Geneva, Switzerland, 2025. Disponível em: <https://www.weforum.org/publications/global-risks-report-2025/>. XIE, S. et al. Deepfake detection in the aigc era: A survey, benchmarks, and future perspectives. Information Fusion, Elsevier, p. 103740, 2025. YAN, Z. et al. Df40: Toward next-generation deepfake detection. Advances in Neural Information Processing Systems, v. 37, p. 29387–29434, 2024. ZHANG, A. et al. Dive into Deep Learning. Cambridge University Press, 2023. ISBN 9781009389433. Disponível em: <https://books.google.com.br/books?id=vfDiEAAAQBAJ>. ZHAO, X. et al. A review of convolutional neural networks in computer vision. Artificial Intelligence Review, v. 57, n. 4, 2024. | |
| dc.rights | Attribution-NonCommercial-NoDerivs 3.0 United States | en |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/3.0/us/ | |
| dc.subject | Deepfakes | |
| dc.subject | Visão computacional | |
| dc.subject | Redes neurais convolucionais | |
| dc.subject | Transferência de aprendizado | |
| dc.subject | Inteligência artificial. | |
| dc.title | Transferência de aprendizado em redes neurais convolucionais para detecção de deepfakes faciais. | |
| dc.title.alternative | Transfer Learning in Convolutional Neural Networks for Facial Deepfake Detection. | |
| dc.type | Trabalho de Conclusão de Curso |
Arquivos
Pacote original
1 - 1 de 1
Carregando...
- Nome:
- Redes_neurais_transferência_aprendizado_deepfakes.pdf
- Tamanho:
- 6.8 MB
- Formato:
- Adobe Portable Document Format