Journals / Bilişim Teknolojileri Dergisi / 2026 / Cilt: 19 Sayı: 1

Comprehensive Dataset for Analyzing Detectability in LSB Steganography

LSB Steganografisinde Tespit Edilebilirliğin Analizi İçin Kapsamlı Bir Veri Seti

Emir Öztürk(TRAKYA ÜNİVERSİTESİ, MÜHENDİSLİK FAKÜLTESİ, BİLGİSAYAR MÜHENDİSLİĞİ BÖLÜMÜ)0000-0002-3734-5171
Andaç Mesut(Trakya Üniversitesi, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü)0000-0003-0853-5256
Özlem Aydın Fidan(Trakya Üniversitesi, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü)0000-0002-6401-4183
Pages
79–90
Publication Date
2026-01-31
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

It provides a valuable resource for developing and evaluating new deep learning techniques in steganography and enhancing digital information security methods.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Steganography involves concealing secret information within selected cover media to prevent detection of its existence, complementing cryptography by enhancing information security.
📊
Key Findings & Data:Among various steganographic methods, Least Significant Bit (LSB) embedding stands out due to its simplicity, efficiency, and widespread applicability, particularly in digital images.
💡
Conclusion & Impact:It provides a valuable resource for developing and evaluating new deep learning techniques in steganography and enhancing digital information security methods.
🔬Design:Araştırma Makalesi
📍Scope:Comprehensive Sample
⚙️Variables:LSB · steganografi · veriseti

Abstract

Steganography involves concealing secret information within selected cover media to prevent detection of its existence, complementing cryptography by enhancing information security. Among various steganographic methods, Least Significant Bit (LSB) embedding stands out due to its simplicity, efficiency, and widespread applicability, particularly in digital images. Although many researchers have studied steganographic methods, there is still a lack of standard datasets to effectively test and compare LSB methods. To address this gap, this study introduces a large and well-organized dataset consisting of 432,000 steganographic images. The images are selected from high-resolution sources and resized into four different sizes: 128×128, 256×256, 512×512, and 1024×1024 pixels. Secret messages hidden within these images are drawn from texts in six languages—German, English, Spanish, French, Italian, and Turkish—to analyze linguistic effects on steganographic detectability. Each image includes detailed metadata about the hidden information, such as the number of bits used per pixel, image size, message length, and whether the embedding is sequential or random. The dataset enables researchers to investigate how factors like message length, embedding randomness, and language differences impact the detectability of hidden messages. It provides a valuable resource for developing and evaluating new deep learning techniques in steganography and enhancing digital information security methods.

Özet

Steganografi, gizli bilgilerin seçilen bir ortam içerisine gizlenerek varlığının tespit edilmesini engellemeyi amaçlayan, kriptografiyi tamamlayarak bilgi güvenliğini artıran bir tekniktir. Çeşitli steganografik yöntemler arasında, özellikle sayısal görüntülerde yaygın olarak kullanılan En Önemsiz Bit (Least Significant Bit - LSB) yerleştirme yöntemi, işlem kolaylığı ve geniş uygulama alanı ile öne çıkmaktadır. Steganografi yöntemleri üzerine birçok çalışma yapılmış olsa da LSB yönteminin etkin bir şekilde test edilip karşılaştırılabilmesini sağlayacak standart bir veri setinin eksikliği devam etmektedir. Bu eksikliği gidermek amacıyla bu çalışmada, 432.000 steganografik görüntüden oluşan kapsamlı ve sistemli bir veri seti ve bu veri seti üzerinde tespit edilebilirliğin bir analizi sunulmaktadır. Görüntüler yüksek çözünürlüklü kaynaklardan seçilmiş ve 128×128, 256×256, 512×512 ve 1024×1024 piksel olmak üzere dört farklı çözünürlükte elde edilmiştir. Bu görüntülere gizlenen mesajlar, steganografinin dile bağlı tespit edilebilirliğine yönelik analizler yapabilmek amacıyla Almanca, İngilizce, İspanyolca, Fransızca, İtalyanca ve Türkçe olmak üzere altı farklı dilden alınan metinlerden elde edilmiştir. Her bir görüntü, piksel başına kullanılan bit sayısı, görüntü boyutu, mesaj uzunluğu ve gizleme işleminin sıralı mı yoksa rastgele mi yapıldığı gibi bilgileri içeren detaylı bir metadata ile birlikte sunulmaktadır. Çalışmada sunulan veri seti, mesaj uzunluğu, gizleme yöntemi ve dil farklılıkları gibi etmenlerin gizli bilginin tespit edilebilirliği üzerindeki etkilerinin araştırılmasına olanak tanımaktadır. Ayrıca, derin öğrenme tabanlı yeni steganaliz yöntemlerinin geliştirilmesi ve değerlendirilmesi için değerli bir kaynak sunmakta, dijital bilgi güvenliğinin artırılmasına katkı sağlamaktadır.

🔖

Cite This Article

Öztürk, E., Mesut, A., Fidan, Ö. A. (2026). Comprehensive Dataset for Analyzing Detectability in LSB Steganography. Bilişim Teknolojileri Dergisi, Cilt: 19 Sayı: 1, 79–90. https://doi.org/10.17671/gazibtd.1690579

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (44)

  1. L. Chen, R. Wang, D. Yan, and J. Wang, “Learning to Generate Steganographic Cover for Audio Steganography Using GAN,” IEEE Access, vol. 9, pp. 88098–88107, 2021, doi: 10.1109/ACCESS.2021.3090445.
  2. A. A. Alsabhany, F. Ridzuan, and A. H. Azni, “The Adaptive Multi-Level Phase Coding Method in Audio Steganography,” IEEE Access, vol. 7, pp. 129291–129306, 2019, doi: 10.1109/ACCESS.2019.2940640.
  3. M. H. Noor Azam, F. Ridzuan, M. N. S. Mohd Sayuti, A. H. Azni, N. H. Zakaria, and V. Potdar, “A systematic review on cover selection methods for steganography: Trend analysis, novel classification and analysis of the elements,” Computer Science Review, vol. 56, p. 100726, May 2025, doi: 10.1016/j.cosrev.2025.100726.
  4. C. E. Shannon, “Communication theory of secrecy systems,” The Bell System Technical Journal, vol. 28, no. 4, pp. 656–715, Oct. 1949, doi: 10.1002/j.1538-7305.1949.tb00928.x.
  5. J. Li, K. Wang, and X. Jia, “A Coverless Audio Steganography Based on Generative Adversarial Networks,” Electronics, vol. 12, no. 5, Art. no. 5, Jan. 2023, doi: 10.3390/electronics12051253.
  6. M. A. Nasr et al., “A robust audio steganography technique based on image encryption using different chaotic maps,” Sci Rep, vol. 14, no. 1, p. 22054, Sept. 2024, doi: 10.1038/s41598-024-70940-3.
  7. F. Li, Z. Yu, K. Wu, C. Qin, and X. Zhang, “Multi-Modality Ensemble Distortion for Spatial Steganography With Dynamic Cost Correction,” IEEE Transactions on Dependable and Secure Computing, vol. 21, no. 4, pp. 1557–1571, July 2024, doi: 10.1109/TDSC.2023.3285590.
  8. Z. Saeidi, A. Yazdi, S. Mashhadi, M. Hadian, and A. Gutub, “High performance image steganography integrating IWT and Hamming code within secret sharing,” IET Image Processing, vol. 18, no. 1, pp. 129–139, 2024, doi: 10.1049/ipr2.12938.
  9. F. Ernawan, “An improved hiding information by modifying selected DWT coefficients in video steganography,” Multimed Tools Appl, vol. 83, no. 12, pp. 34629–34645, Apr. 2024, doi: 10.1007/s11042-023-17113-y.
  10. J. Li, M. Zhang, K. Niu, Y. Zhang, Y. Ke, and X. Yang, “High-Security HEVC Video Steganography Method Using the Motion Vector Prediction Index and Motion Vector Difference,” Tsinghua Science and Technology, vol. 30, no. 2, pp. 813–829, Apr. 2025, doi: 10.26599/TST.2024.9010016.
  11. E. Öztürk, A. Ş. Mesut, and Ö. A. Fıdan, “A Character Based Steganography Using Masked Language Modeling,” IEEE Access, vol. 12, pp. 14248–14259, 2024, doi: 10.1109/ACCESS.2024.3354710.
  12. S. N. KL and B. K. R, “Text steganography: enhanced character-level embedding algorithm using font attribute with increased resilience to statistical attacks,” Multimed Tools Appl, May 2024, doi: 10.1007/s11042-024-19272-y.
  13. M. Rahman and others, “An efficient image steganography technique using Huffman coding and LSB substitution with multi-level encryption,” Scientific Reports, vol. 13, no. 1, pp. 1–12, 2023.
  14. S. Alanzy and others, “Multi-level steganography using AES and Blowfish with randomized LSB embedding,” Applied Sciences, vol. 13, no. 7, p. 4345, 2023.
  15. M. Rahman and others, “An efficient RGB channel-based LSB steganography technique for reliable data embedding,” Scientific Reports, vol. 15, no. 1, pp. 1–14, 2025.
  16. I. Guarino, G. Aceto, D. Ciuonzo, A. Montieri, V. Persico, and A. Pescapè, “Explainable Deep-Learning Approaches for Packet-Level Traffic Prediction of Collaboration and Communication Mobile Apps,” IEEE Open Journal of the Communications Society, vol. 5, pp. 1299–1324, 2024, doi: 10.1109/OJCOMS.2024.3366849.
  17. A. M. Abdallah, A. Saif Rashed Obaid Alkaabi, G. Bark Nasser Douman Alameri, S. H. Rafique, N. S. Musa, and T. Murugan, “Cloud Network Anomaly Detection Using Machine and Deep Learning Techniques— Recent Research Advancements,” IEEE Access, vol. 12, pp. 56749–56773, 2024, doi: 10.1109/ACCESS.2024.3390844.
  18. S. A. Sheik and S. Durai, “Cryptography with optimal deep learning-based authentication scheme for preserving anonymity in telecare medical information system,” Multimed Tools Appl, Apr. 2024, doi: 10.1007/s11042-024-19194-9.
  19. E. Abdellatef, E. A. Naeem, and F. E. A. El-Samie, “DeepEnc: deep learning-based CT image encryption approach,” Multimed Tools Appl, vol. 83, no. 4, pp. 11147–11167, Jan. 2024, doi: 10.1007/s11042-023-15818-8.
  20. W. Su, J. Ni, and Y. Sun, “StegaStyleGAN: Towards Generic and Practical Generative Image Steganography,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 1, Art. no. 1, Mar. 2024, doi: 10.1609/aaai.v38i1.27776.
  21. S. Pramanik, “An adaptive image steganography approach depending on integer wavelet transform and genetic algorithm,” Multimed Tools Appl, vol. 82, no. 22, pp. 34287–34319, Sept. 2023, doi: 10.1007/s11042-023-14505-y.
  22. T. Wang et al., “Lossless image steganography: Regard steganography as super-resolution,” Information Processing & Management, vol. 61, no. 4, p. 103719, July 2024, doi: 10.1016/j.ipm.2024.103719.
  23. Y. Zhou, T. Luo, Z. He, G. Jiang, H. Xu, and C.-C. Chang, “CAISFormer: Channel-wise attention transformer for image steganography,” Neurocomputing, vol. 603, p. 128295, Oct. 2024, doi: 10.1016/j.neucom.2024.128295.
  24. Z. Yang, K. Wang, S. Ma, Y. Huang, X. Kang, and X. Zhao, “Istego100k: Large-scale image steganalysis dataset,” in International Workshop on Digital Watermarking, Springer, 2019, pp. 352–364.
  25. M. Zuppelli, “Stego-Images Dataset.” 2019. [Online]. Available: https://www.kaggle.com/datasets/marcozuppelli/stegoimagesdataset
  26. M. Guarascio, M. Zuppelli, N. Cassavia, L. Caviglione, and G. Manco, “Revealing MageCart-like threats in favicons via artificial intelligence,” in Proceedings of the 17th International Conference on Availability, Reliability and Security (ARES), 2022, pp. 1–7. [Online]. Available: https://github.com/Ocram95/Stego-Favicons-Dataset
  27. J. D. Miranda and D. J. Parada, “LSB steganography detection in monochromatic still images using artificial neural networks,” Multimedia Tools and Applications, vol. 81, no. 1, pp. 785–805, 2022.
  28. D. Das, A. Durafe, and V. Patidar, “An Efficient Lightweight LSB Steganography with deep learning steganalysis,” in Computational Intelligence in Image and Video Processing, Chapman and Hall/CRC, 2023, pp. 131–154.
  29. K. Angulo, D. Gil, A. Yáñez, and H. Espitia, “Hybrid CNN-NLP Model for Detecting LSB Steganography in Digital Images,” Applied System Innovation, vol. 8, no. 4, p. 107, 2025.
  30. C. Bentz, D. Alikaniotis, M. Cysouw, and R. Ferrer-i-Cancho, “The entropy of words—Learnability and expressivity across more than 1000 languages,” Entropy, vol. 19, no. 6, p. 275, 2017.
  31. C. Coupé, Y. M. Oh, D. Dediu, and F. Pellegrino, “Different languages, similar encoding efficiency: Comparable information rates across the human communicative niche,” Science advances, vol. 5, no. 9, p. eaaw2594, 2019.
  32. A. Ignatov, R. Timofte, and others, “PIRM challenge on perceptual image enhancement on smartphones: report,” in European Conference on Computer Vision (ECCV) Workshops, Jan. 2019.
  33. R. Timofte et al., “NTIRE 2018 Challenge on Single Image Super-Resolution: Methods and Results,” in The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, June 2018.
  34. R. Timofte et al., “NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results,” in The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, July 2017.
  35. E. Agustsson and R. Timofte, “NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study,” in The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, July 2017.
  36. “From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions | Transactions of the Association for Computational Linguistics | MIT Press.” Accessed: Mar. 23, 2025. [Online]. Available: https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00166/43313/From-image-descriptions-to-visual-denotations-New
  37. SkySyrup, “tinystories_german.” 2025. [Online]. Available: https://huggingface.co/datasets/SkySyrup/tinystories_german
  38. agentlans, “high-quality-english-sentences.” 2025. [Online]. Available: https://huggingface.co/datasets/agentlans/high-quality-english-sentences
  39. proxectonos, “arn-es-30M.” 2025. [Online]. Available: https://huggingface.co/datasets/proxectonos/arn-es-30M
  40. eckendoerffer, “news_fr.” 2025. [Online]. Available: https://huggingface.co/datasets/eckendoerffer/news_fr
  41. alberto98fx, “Letteratura-Italiana.” 2025. [Online]. Available: https://huggingface.co/datasets/alberto98fx/Letteratura-Italiana
  42. zares, “wiki.tr.txt.” 2025. [Online]. Available: https://huggingface.co/datasets/zares/wiki.tr.txt
  43. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning,” Image Recognition, vol. 7, no. 4, pp. 327–336, 2015.
  44. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778.