STEGS2GAN - Um Modelo de Aprendizado Profundo para Esteganografia e Esteganálise em Imagens Digitais utilizando Redes Adversárias Generativas
Resumo
Este trabalho descreve o desenvolvimento de um modelo de aprendizado profundo para realizar esteganografia e esteganálise em imagens digitais. A arquitetura do modelo utiliza uma Rede Adversária Generativa (GAN), cujo gerador é treinado para ocultar dados textuais em imagens imperceptivelmente e o discriminador para detectar anomalias que podem indicar ocultação de textos em imagens. O objetivo é criar um treinamento competitivo para avaliar o equilíbrio entre a qualidade visual da imagem, a taxa de recuperação da informação oculta e a resistência à detecção. A metodologia explora a adaptação de redes profundas residuais utilizando ambiente adversarial para a criação de padrões de ocultação robustos.Referências
Agustsson, E., Timofte, R. (2017) “NTIRE 2017 Challenge on Single Image SuperResolution: Dataset and Study”. 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Honolulu, HI, USA, p. 1122-1131.
Arjovsky, M., Chintala, S., Bottou, L. (2017) “Wasserstein GAN”. Proceedings of the 34th International Conference on Machine Learning (ICML), Sydney, Austrália, p. 214-223. Disponível em: [link].
Boroumand, M., Chen, M., Fridrich, J. (2019) “Deep Residual Network for Steganalysis of Digital Images”, IEEE Transactions on Information Forensics and Security, v. 14, n. 5, p. 1181-1193.
Cheddad, A., Condell, J., Curran, K., Mc Kevitt, P. (2010) “Digital image steganography: Survey and analysis of current methods”. Signal Processing, v. 90, n. 3, p. 727-752.
Fridrich, J. (2009) Steganography in Digital Media: Principles, Algorithms, and Applications. Cambridge: Cambridge University Press.
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y. (2014) “Generative Adversarial Nets”. Advances in Neural Information Processing Systems (NIPS), v. 27, p. 2672-2680.
Isola, P., Zhu, J., Zhou, T., Efros, A. (2017) “Image-to-Image Translation with Conditional Adversarial Networks”. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, p. 5967-5976.
Kessler, G. (2004) “An Overview of Steganography for the Computer Forensics Examiner”. Forensic Science Communications, v. 6, n. 3, p. 1-27.
Khoma, D., Bashkov, Y. (2025) “Enhanced Image Steganography with Keras-SteganoGAN: A TensorFlow-Based GAN”, Scientific Papers of Donetsk National Technical University. Series: Computer Engineering and Automation, v. 3, n. 5, p. 48-59.
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., Zitnick, C. L. (2014) “Microsoft COCO: Common Objects in Context”. European Conference on Computer Vision (ECCV), Zurique, Suíça, p. 740-755.
Peng, Y., Yu, O., Fu, G., Zhang, W., Duan, C. (2024) “Improving the robustness of steganalysis in the adversarial environment with generative adversarial network”, Journal of Information Security and Applications, v. 82, 103743.
Qin, J., Wang, J., Tan, Y., Huang, H., Xiang, X., He, Z. (2020) “Coverless Image Steganography Based on Generative Adversarial Network”. Mathematics, v. 8, n. 9, 1394.
Wang, Z., Bovik, A., Sheikh, H., Simoncelli, E. (2004) “Image Quality Assessment: From Error Visibility to Structural Similarity”, IEEE Transactions on Image Processing, v. 13, n. 4, p. 600-612.
You, W., Zhang, H., Zhao, X. (2020) “A Siamese CNN for Image Steganalysis”, IEEE Transactions on Information Forensics and Security, v. 16, p. 291-306.
Zhang, H., Song, Z., Xing, Q., Feng, B., Lin, X. (2022) “A Generative Learning Steganalysis Network against the Problem of Training-Images-Shortage”. Electronics, v. 11, n. 20, 3331.
Zhang, K., Cuesta-Infante, A., Xu, L., Veeramachaneni, K. (2019) “SteganoGAN: High Capacity Image Steganography with GANs”. arXiv preprint, arXiv:1901.03892.
Arjovsky, M., Chintala, S., Bottou, L. (2017) “Wasserstein GAN”. Proceedings of the 34th International Conference on Machine Learning (ICML), Sydney, Austrália, p. 214-223. Disponível em: [link].
Boroumand, M., Chen, M., Fridrich, J. (2019) “Deep Residual Network for Steganalysis of Digital Images”, IEEE Transactions on Information Forensics and Security, v. 14, n. 5, p. 1181-1193.
Cheddad, A., Condell, J., Curran, K., Mc Kevitt, P. (2010) “Digital image steganography: Survey and analysis of current methods”. Signal Processing, v. 90, n. 3, p. 727-752.
Fridrich, J. (2009) Steganography in Digital Media: Principles, Algorithms, and Applications. Cambridge: Cambridge University Press.
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y. (2014) “Generative Adversarial Nets”. Advances in Neural Information Processing Systems (NIPS), v. 27, p. 2672-2680.
Isola, P., Zhu, J., Zhou, T., Efros, A. (2017) “Image-to-Image Translation with Conditional Adversarial Networks”. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, p. 5967-5976.
Kessler, G. (2004) “An Overview of Steganography for the Computer Forensics Examiner”. Forensic Science Communications, v. 6, n. 3, p. 1-27.
Khoma, D., Bashkov, Y. (2025) “Enhanced Image Steganography with Keras-SteganoGAN: A TensorFlow-Based GAN”, Scientific Papers of Donetsk National Technical University. Series: Computer Engineering and Automation, v. 3, n. 5, p. 48-59.
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., Zitnick, C. L. (2014) “Microsoft COCO: Common Objects in Context”. European Conference on Computer Vision (ECCV), Zurique, Suíça, p. 740-755.
Peng, Y., Yu, O., Fu, G., Zhang, W., Duan, C. (2024) “Improving the robustness of steganalysis in the adversarial environment with generative adversarial network”, Journal of Information Security and Applications, v. 82, 103743.
Qin, J., Wang, J., Tan, Y., Huang, H., Xiang, X., He, Z. (2020) “Coverless Image Steganography Based on Generative Adversarial Network”. Mathematics, v. 8, n. 9, 1394.
Wang, Z., Bovik, A., Sheikh, H., Simoncelli, E. (2004) “Image Quality Assessment: From Error Visibility to Structural Similarity”, IEEE Transactions on Image Processing, v. 13, n. 4, p. 600-612.
You, W., Zhang, H., Zhao, X. (2020) “A Siamese CNN for Image Steganalysis”, IEEE Transactions on Information Forensics and Security, v. 16, p. 291-306.
Zhang, H., Song, Z., Xing, Q., Feng, B., Lin, X. (2022) “A Generative Learning Steganalysis Network against the Problem of Training-Images-Shortage”. Electronics, v. 11, n. 20, 3331.
Zhang, K., Cuesta-Infante, A., Xu, L., Veeramachaneni, K. (2019) “SteganoGAN: High Capacity Image Steganography with GANs”. arXiv preprint, arXiv:1901.03892.
Publicado
01/09/2026
Como Citar
SOUZA, João Pedro B. S.; CORREIA, Breno W. B.; TREVISANI, Kleber M..
STEGS2GAN - Um Modelo de Aprendizado Profundo para Esteganografia e Esteganálise em Imagens Digitais utilizando Redes Adversárias Generativas. In: WORKSHOP DE TRABALHOS DE INICIAÇÃO CIENTÍFICA E DE GRADUAÇÃO - SIMPÓSIO BRASILEIRO DE CIBERSEGURANÇA (SBSEG), 26. , 2026, Armação dos Búzios/RJ.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 727-737.
DOI: https://doi.org/10.5753/sbseg_estendido.2026.29255.
