Performance Evaluation of Steganogan Using Hybrid Image Datasets and Statistical Quality Metrics

Öz

This study proposes a novel approach by employing SteganoGAN, a steganographic framework based on Generative Adversarial Networks (GANs). The impact of image categories with different semantic contents (art, building, and nature) on system performance was examined in detail using the SteganoGAN architecture. A hybrid dataset composed of BossBase and USC-SIPI images was utilized to conduct the experiments. The influence of image quality, categorized by visual content, on performance was systematically analyzed. In particular, changes in skewness and kurtosis values, as well as the widely used image quality metrics PSNR and SSIM, were investigated. Experimental results demonstrated that nature images provided superior performance, achieving an SSIM value of 99.59 and exhibiting the lowest skewness deviation from the original cover images.

Anahtar Kelimeler

• SteganoGan
• Generative Adversarial Networks
• Steganography

Hibrit Görüntü Veri Setti ve İstatistiksel Metrikler ile Steganogan'ın Performansının Değerlendirilmesi

Öz

Bu çalışma, çekişmeli üretici ağ tabanlı bir steganografi yöntemi olan SteganoGAN’ı kullanarak yenilikçi bir yaklaşım önermektedir. SteganoGAN mimarisi kullanılarak, farklı türde görüntü kategorilerinin (sanatsal, yapı ve doğa) sistem performansı üzerindeki etkisi detaylı şekilde incelenmiştir. Deneylerde, BossBase ve USC-SIPI görüntülerinden oluşan hibrit bir veri seti kullanılmıştır. Görsel içeriğe göre sınıflandırılan görüntü kalitesinin performansa etkisi sistematik olarak analiz edilmiştir. Özellikle, çarpıklık (skewness) ve basıklık (kurtosis) değerlerindeki değişimler ile yaygın olarak kullanılan görüntü kalite metrikleri olan PSNR ve SSIM incelenmiştir. Deneysel sonuçlar, doğa görüntülerinin üstün performans sağladığını, %99,59 SSIM değeri elde ettiğini ve orijinal görüntülere kıyasla en düşük çarpıklık sapmasını gösterdiğini ortaya koymuştur.

Anahtar Kelimeler

• SteganoGAN
• Çekişmeli Yapay Sinir Ağları
• Steganografi

Kaynakça

1. Abdulwahed, M. N. (2020). An effective and secure digital image steganography scheme using two random function and chaotic map.
2. Abuzanouneh, K. I. M., & Hadwan, M. (2021). Multi-stage protection using pixel selection technique for enhancing steganography. International Journal of Communication Networks and Information Security (IJCNIS), 13(1), 55–61. https://doi.org/10.17762/IJCNIS.V13I1.4907
3. Ahmad, S., Ogala, J. O., Ikpotokin, F., Arif, M., Ahmad, J., & Mehfuz, S. (2024). Enhanced CNN-DCT steganography: Deep learning-based image steganography over cloud. SN Computer Science, 5(4). https://doi.org/10.1007/S42979-024-02756-X
4. Alanzy, M., Alomrani, R., Alqarni, B., & Almutairi, S. (2023). Image steganography using LSB and hybrid encryption algorithms. Applied Sciences, 13(21), 11771. https://doi.org/10.3390/APP132111771
5. Ali, A., Esam, E., Bayoumi, R., Tawfik, A., Abdulrahman, O., Saad, S., Ashraf, B. M., & Ihab, S. (2023). Steganography platform. Proceedings of the 11th IEEE International Conference on Intelligent Computing and Information Systems (ICICIS 2023), 536–541. https://doi.org/10.1109/ICICIS58388.2023.10391186
6. An, Y., Yu, N., Zhang, S., Liu, H., & Duan, J. (2022). ACGAN based coverless image steganography method. Proceedings of SPIE, 12294, 1035–1040. https://doi.org/10.1117/12.2639718
7. Ansari, A. S., Mohammadi, M. S., & Parvez, M. T. (2020). A multiple-format steganography algorithm for color images. IEEE Access, 8, 83926–83939. https://doi.org/10.1109/ACCESS.2020.2991130
8. Bai, Y., Zhang, Y., Ding, M., & Ghanem, B. (2018). SOD-MTGAN: Small object detection via multi-task generative adversarial network. In European Conference on Computer Vision (Vol. 11217, pp. 210–226). Springer. https://doi.org/10.1007/978-3-030-01261-8_13

9. Bui, T., Agarwal, S., Yu, N., & Collomosse, J. (2023). RoSteALS: Robust steganography using autoencoder latent space. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (pp. 933–942). https://doi.org/10.1109 /CVPRW59228.2023.00100
10. Cai, L., & Wang, W. Y. (2018). KBGAN: Adversarial learning for knowledge graph embeddings. In NAACL HLT 2018: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Vol. 1, pp. 1470–1480). https://doi.org/10.18653/v1/n18-1133
11. Chatterjee, A., Ghosal, S. K., & Sarkar, R. (2020). LSB based steganography with OCR: An intelligent amalgamation. Multimedia Tools and Applications, 79(17–18), 11747–11765. https://doi.org/10.1007/S11042-019-08472-6
12. Chen, M., He, P., & Liu, J. (2022). HLTD-CSA: Cover selection algorithm based on hybrid local texture descriptor for color image steganography. Journal of Visual Communication and Image Representation, 89, 103646. https://doi.org/10.1016/J.JVCIR.2022.103646
13. Dai, W., Dong, N., Wang, Z., Liang, X., Zhang, H., & Xing, E. P. (2018). SCAN: Structure correcting adversarial network for organ segmentation in chest X-rays. In Medical Image Computing and Computer Assisted Intervention (Vol. 11045, pp. 263–273). Springer. https://doi.org/10.1007/978-3-030-00889-5_30
14. Datta, B., Dutta, K., & Roy, S. (2020). Data hiding in virtual bit-plane using efficient Lucas number sequences. Multimedia Tools and Applications, 79(31–32), 22673–22703. https://doi.org/10.1007/S11042-020-08979-3 DeOldify. (2024). Home. https://deoldify.ai/
15. Donahue, C., Li, B., & Prabhavalkar, R. (2018). Exploring speech enhancement with generative adversarial networks for robust speech recognition. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 5024–5028). https://doi.org/10.1109/ICASSP.2018.8462581
16. Duan, X., Guo, D., Liu, N., Li, B., Gou, M., & Qin, C. (2020). A new high capacity image steganography method combined with image elliptic curve cryptography and deep neural network. IEEE Access, 8, 25777–25788. https://doi.org/10.1109/ACCESS.2020.2971528
17. Duan, X., Liu, N., Gou, M., Wang, W., & Qin, C. (2020). SteganoCNN: Image steganography with generalization ability based on convolutional neural network. Entropy, 22(10), 1–15. https://doi.org/10.3390/E22101140
18. El-Nouby, A., Sharma, S., Schulz, H., Hjelm, D., El Asri, L., Ebrahimi Kahou, S., Bengio, Y., & Taylor, G. W. (2019). Tell, draw, and repeat: Generating and modifying images based on continual linguistic instruction. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 10304–10312.
19. Fakhredanesh, M., Rahmati, M., & Safabakhsh, R. (2019). Steganography in discrete wavelet transform based on human visual system and cover model. Multimedia Tools and Applications, 78(13), 18475–18502. https://doi.org/10.1007/S11042-019-7238-8
20. Google for Developers. (n.d.). Overview of GAN structure. https://developers.google.com/machine-learning/gan/gan_structure
21. Guimaraes, G., Sanchez-Lengeling, B., Outeiral, C., Luis, P., Farias, C., & Aspuru-Guzik, A. (2017). Objective-reinforced generative adversarial networks (ORGAN) for sequence generation models. arXiv. https://arxiv.org/abs/1705.10843v3
22. Han, Y., Zhang, P., Huang, W., Zha, Y., Cooper, G. D., & Zhang, Y. (2020). Robust visual tracking based on adversarial unlabeled instance generation with label smoothing loss regularization. Pattern Recognition, 97, 107027. https://doi.org/10.1016/J.PATCOG.2019.107027
23. Hassaballah, M., Hameed, M. A., Awad, A. I., & Muhammad, K. (2021). A novel image steganography method for industrial Internet of Things security. IEEE Transactions on Industrial Informatics, 17(11), 7743–7751. https://doi.org/10.1109/TII.2021.3053595
24. Hu, W., & Tan, Y. (2017). Generating adversarial malware examples for black-box attacks based on GAN. Communications in Computer and Information Science, 1745, 409–423. https://doi.org/10.1007/978-981-19-8991-9_29
25. Huo, L., Chen, R., Wei, J., & Huang, L. (2024). A high-capacity and high-security image steganography network based on chaotic mapping and generative adversarial networks. Applied Sciences, 14(3), 1225. https://doi.org/10.3390/APP14031225
26. Hwang, J.-J., Azernikov, S., Efros, A. A., & Yu, S. X. (2018). Learning beyond human expertise with generative models for dental restorations. arXiv. https://arxiv.org/abs/1804.00064v1
27. Iizuka, S., Simo-Serra, E., & Ishikawa, H. (2017). Globally and locally consistent image completion. ACM Transactions on Graphics, 36(4). https://doi.org/10.1145/3072959.3073659
28. Kadhim, I. J., Premaratne, P., & Vial, P. J. (2020). High capacity adaptive image steganography with cover region selection using dual-tree complex wavelet transform. Cognitive Systems Research, 60, 20–32. https://doi.org/10.1016/J.COGSYS.2019.11.002
29. Ke, Y., Zhang, M. Q., Liu, J., Su, T. T., & Yang, X. Y. (2019). Generative steganography with Kerckhoffs’ principle. Multimedia Tools and Applications, 78(10), 13805–13818. https://doi.org/10.1007/S11042-018-6640-
30. Kordov, K., & Zhelezov, S. (2021). Steganography in color images with random order of pixel selection and encrypted text message embedding. PeerJ Computer Science, 7, 1–21. https://doi.org/10.7717/PEERJ-CS.380
31. Kuppusamy, P. G., Ramya, K. C., Rani, S. S., Sivaram, M., & Dhasarathan, V. (2020). A novel approach based on modified cycle generative adversarial networks for image steganography. Scalable Computing: Practice and Experience, 21(1), 63–72. https://doi.org/10.12694/SCPE.V21I1.1613
32. Laishram, D., & Tuithung, T. (2021). A novel minimal distortion-based edge adaptive image steganography scheme using local complexity: (BEASS). Multimedia Tools and Applications, 80(1), 831–854. https://doi.org/10.1007/S11042-020-09519-9
33. Ledig, C., Theis, L., Huszár, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z., & Shi, W. (2017). Photo-realistic single image super-resolution using a generative adversarial network. *Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)*, 4681–4690. https://doi.org/10.1109/CVPR.2017.19
34. Liao, X., Li, K., & Yin, J. (2017). Separable data hiding in encrypted image based on compressive sensing and discrete Fourier transform. Multimedia Tools and Applications, 76(20), 20739–20753. https://doi.org/10.1007/S11042-016-3971-4
35. Liu, F., Jiao, L., & Tang, X. (2019). Task-oriented GAN for PolSAR image classification and clustering. IEEE Transactions on Neural Networks and Learning Systems, 30(9), 2707–2719. https://doi.org/10.1109/TNNLS.2018.2885799
36. Liu, Q., Zhou, H., Xu, Q., Liu, X., & Wang, Y. (2021). PSGAN: A generative adversarial network for remote sensing image pan-sharpening. IEEE Transactions on Geoscience and Remote Sensing, 59(12), 10227–10242. https://doi.org/10.1109/TGRS.2020.3042974
37. Liu, W., Hou, X., Duan, J., & Qiu, G. (2020). End-to-end single image fog removal using enhanced cycle consistent adversarial networks. IEEE Transactions on Image Processing, 29, 7819–7833. https://doi.org/10.1109/TIP.2020.3007844
38. Lu, S. P., Wang, R., Zhong, T., & Rosin, P. L. (2021). Large-capacity image steganography based on invertible neural networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 10811–10820). https://doi.org/10.1109/CVPR46437.2021.01067
39. Lutz, S., Amplianitis, K., & Smolic, A. (2018). AlphaGAN: Generative adversarial networks for natural image matting. In British Machine Vision Conference 2018. https://arxiv.org/abs/1807.10088v1
40. Ma, L., Jia, X., Sun, Q., Schiele, B., Tuytelaars, T., & Van Gool, L. (2017). Pose guided person image generation. In Advances in Neural Information Processing Systems (Vol. 2017-December, pp. 406–416). https://arxiv.org/abs/1705.09368v6
41. Maji, G., Mandal, S., & Sen, S. (2021). Cover independent image steganography in spatial domain using higher order pixel bits. Multimedia Tools and Applications, 80(10), 15977–16006. https://doi.org/10.1007/S11042-020-10298-6
42. Mandal, P. C., & Mukherjee, I. (2022). High capacity data hiding based on multi-directional pixel value differencing and decreased difference expansion. Multimedia Tools and Applications, 81(4), 5325–5347. https://doi.org/10.1007/S11042-021-11605-5
43. Martin, A., Hernández, A., Alazab, M., Jung, J., & Camacho, D. (2023). Evolving generative adversarial networks to improve image steganography. Expert Systems with Applications, 222, 119841. https://doi.org/10.1016/J.ESWA.2023.119841
44. Miri, A., & Faez, K. (2017). Adaptive image steganography based on transform domain via genetic algorithm. Optik, 145, 158–168. https://doi.org/10.1016/J.IJLEO.2017.07.043
45. Mogren, O. (2016). C-RNN-GAN: Continuous recurrent neural networks with adversarial training. arXiv. https://arxiv.org/abs/1611.09904v1
46. Pan, J., Ferrer C.C., McGuinness K., O'Connor N.E., Torres J., Sayrol E. & Giro-i-Nieto X: (2017). SalGAN: Visual saliency prediction with generative adversarial networks. arXiv. https://arxiv.org/abs/1701.01081v3
47. Pascual, S., Bonafonte, A., & Serra, J. (2017). SEGAN: Speech enhancement generative adversarial network. In Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH) (pp. 3642–3646). https://doi.org/10.21437/Interspeech.2017-1428
48. Ramandi, V. Y., Fateh, M., & Rezvani, M. (2024). VidaGAN: Adaptive GAN for image steganography. IET Image Processing, 18(12), 3329–3342. https://doi.org/10.1049/IPR2.13177
49. Ratzlaff, N., & Fuxin, L. (2019). HyperGAN: A generative model for diverse, performant neural networks. In Proceedings of the 36th International Conference on Machine Learning (Vol. 2019-June, pp. 9371–9381). https://arxiv.org/abs/1901.11058v3
50. Saad, A. H. S., Mohamed, M. S., & Hafez, E. H. (2021). Coverless image steganography based on optical mark recognition and machine learning. IEEE Access, 9, 16522–16531. https://doi.org/10.1109/ACCESS.2021.3050737
51. Saeed, A., Fawad, Khan, M. J., Shahid, H., Naqvi, S. I., Riaz, M. A., Khan, M. S., & Amin, Y. (2020). An accurate texture complexity estimation for quality-enhanced and secure image steganography. IEEE Access, 8, 21613–21630. https://doi.org/10.1109/ACCESS.2020.2968217
52. Saeedi, Z., Yazdi, A., Mashhadi, S., Hadian, M., & Gutub, A. (2024). High performance image steganography integrating IWT and Hamming code within secret sharing. IET Image Processing, 18(1), 129–139. https://doi.org/10.1049/IPR2.12938
53. Saha, S., Chakraborty, A., Chatterjee, A., Dhargupta, S., Ghosal, S. K., & Sarkar, R. (2020). Extended exploiting modification direction based steganography using hashed-weightage array. Multimedia Tools and Applications, 79(29–30), 20973–20993. https://doi.org/10.1007/S11042-020-08951-1
54. Schlegl, T., Seeböck, P., Waldstein, S. M., Schmidt-Erfurth, U., & Langs, G. (2017). Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. In Information Processing in Medical Imaging (Vol. 10265, pp. 146–147). Springer. https://doi.org/10.1007/978-3-319-59050-9_12
55. Shah, P. D., & Bichkar, R. S. (2020). Genetic algorithm based approach to select suitable cover image for image steganography. In 2020 International Conference for Emerging Technology (INCET 2020). https://doi.org/10.1109/INCET49848.2020.9154032
56. Shaik, A., & Thanikaiselvan, V. (2019). High capacity reversible data hiding using 2D parabolic interpolation. Multimedia Tools and Applications, 78(8), 9717–9735. https://doi.org/10.1007/S11042-018-6544-X
57. Shi, H., Dong, J., Wang, W., Qian, Y., & Zhang, X. (2018). SSGAN: Secure steganography based on generative adversarial networks. In Information Security and Cryptology (Vol. 10735, pp. 534–544). Springer. https://doi.org/10.1007/978-3-319-77380-3_51
58. Shi, W., Wang, Z., Zhang, X., & Feng, G. (2026). StarINN: An efficient invertible neural network for image steganography. Displays, 91, 103175. https://doi.org/10.1016/J.DISPLA.2025.103175
59. Shmueli, R., Mishra, D., Shmueli, T., & Hadar, O. (2024). A novel technique for image steganography based on maximum energy seam. Multimedia Tools and Applications, 83(28), 70907–70920. https://doi.org/10.1007/S11042-024-18476-6
60. Shyla, M. K., Kumar, K. B. S., & Das, R. K. (2021). Image steganography using genetic algorithm for cover image selection and embedding. Soft Computing Letters, 3, 100021. https://doi.org/10.1016/J.SOCL.2021.100021
61. Souly, N., Spampinato, C., & Shah, M. (2017). Semi supervised semantic segmentation using generative adversarial network. In Proceedings of the IEEE International Conference on Computer Vision (pp. 5689–5697). https://doi.org/10.1109/ICCV.2017.606
62. Tang, W., Tan, S., Li, B., & Huang, J. (2017). Automatic steganographic distortion learning using a generative adversarial network. IEEE Signal Processing Letters, 24(10), 1547–1551. https://doi.org/10.1109/LSP.2017.2745572
63. Wang, P., Xiong, H., Fu, Y., & Li, X. (2019). Adversarial substructured representation learning for mobile user profiling. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 130–138). https://doi.org/10.1145/3292500.3330869
64. Wang, T. C., Liu M-Y, Zhu J-Y, Liu G., Tao A., Kautz J. & Catanzaro B. (2018). Video-to-video synthesis. In Advances in Neural Information Processing Systems (Vol. 2018-December, pp. 1144–1156). https://arxiv.org/abs/1808.06601v2
65. Wang, W. (2020). A reversible data hiding algorithm based on bidirectional difference expansion. Multimedia Tools and Applications, 79(9–10), 5965–5988. https://doi.org/10.1007/S11042-019-08255-Z
66. Wang, X., Chen, W., Wang, Y. F., & Wang, W. Y. (2018). No metrics are perfect: Adversarial reward learning for visual storytelling. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Vol. 1, pp. 899–909). https://doi.org/10.18653/v1/p18-1083
67. Wang X, Yu K., Shixiang W., Gu J., Liu Y., Dong C., Qiao Y. & Loy C.C. (2018). ESRGAN: Enhanced super-resolution generative adversarial networks. In Computer Vision – ECCV 2018 Workshops (pp. 63–79). Springer. https://doi.org/10.1007/978-3-030-11021-5_5
68. Wang, Z., & Zhang, X. (2018). Secure cover selection for steganography. IEEE Access, 7, 57857–57867. https://doi.org/10.1109/ACCESS.2019.2914226
69. Wang, Z., Feng, G., Shen, L., & Zhang, X. (2023). Cover selection for steganography using image similarity. IEEE Transactions on Dependable and Secure Computing, 20(3), 2328–2340. https://doi.org/10.1109/TDSC.2022.3181039
70. Wang, Z., Zhang, X., & Qian, Z. (2020). Practical cover selection for steganography. IEEE Signal Processing Letters, 27, 71–75. https://doi.org/10.1109/LSP.2019.2956416
71. Wu, H., Zhang, J., Zheng, S., & Huang, K. (2019). GP-GAN: Towards realistic high-resolution image blending. In Proceedings of the 27th ACM International Conference on Multimedia (pp. 2487–2495). https://doi.org/10.1145/3343031.3350944
72. Xie, X. Z., Chang, C. C., & Hu, Y. C. (2020). An adaptive reversible data hiding scheme based on prediction error histogram shifting by exploiting signed-digit representation. Multimedia Tools and Applications, 79(33–34), 24329–24346. https://doi.org/10.1007/S11042-019-08402-6
73. Yeh, R. A., Chen, C., Lim, T. Y., Schwing, A. G., Hasegawa-Johnson, M., & Do, M. N. (2017). Semantic image inpainting with deep generative models. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 6882–6890). https://doi.org/10.1109/CVPR.2017.728
74. Yi, R., Liu, Y. J., Lai, Y. K., & Rosin, P. L. (2019). APDrawingGAN: Generating artistic portrait drawings from face photos with hierarchical GANs. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 10735–10744). https://doi.org/10.1109/CVPR.2019.01100
75. Yin, W., Fu, Y., Sigal, L., & Xue, X. (2017). Semi-latent GAN: Learning to generate and modify facial images from attributes. arXiv. https://arxiv.org/abs/1704.02166v1
76. Younus, Z. S., & Hussain, M. K. (2022). Image steganography using exploiting modification direction for compressed encrypted data. Journal of King Saud University - Computer and Information Sciences, 34(6), 2951–2963. https://doi.org/10.1016/J.JKSUCI.2019.04.008
77. Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., & Huang, T. S. (2018). Generative image inpainting with contextual attention. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 5505–5514). https://doi.org/10.1109/CVPR.2018.00577
78. Zhang, S., Li, H., Li, L., Lu, J., & Zuo, Z. (2022). A high-capacity steganography algorithm based on adaptive frequency channel attention networks. Sensors, 22(20). https://doi.org/10.3390/S22207844
79. Zhang, K. A., Cuesta-Infante, A., Xu, L., & Veeramachaneni, K. (2019). SteganoGAN: High capacity image steganography with GANs. arXiv. https://doi.org/10.48550/arXiv.1901.03892
80. Zhanga, S., Xiaob, Y., Tianc, H., & Lid, X. (2025). A multi-image steganography: ISS. Cybersecurity, 8(1), 1–18. https://doi.org/10.1186/S42400-024-00333-6
81. Zhao, X., & Huang, H. (2021). Research on image steganography based on multiple expansion generation adversarial network. In 2021 IEEE 3rd International Conference on Frontiers Technology of Information and Computer (ICFTIC 2021) (pp. 361–366). https://doi.org/10.1109/ICFTIC54370.2021.9647204
82. Zhou, S., Xiao, T., Yang, Y., Feng, D., He, Q., & He, W. (2017). GeneGAN: Learning object transfiguration and attribute subspace from unpaired data. In British Machine Vision Conference 2017. https://doi.org/10.5244/C.31.111