Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
132 tokens/sec
GPT-4o
28 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Monsters in the Dark: Sanitizing Hidden Threats with Diffusion Models (2310.06951v1)

Published 10 Oct 2023 in cs.CR

Abstract: Steganography is the art of hiding information in plain sight. This form of covert communication can be used by bad actors to propagate malware, exfiltrate victim data, and communicate with other bad actors. Current image steganography defenses rely upon steganalysis, or the detection of hidden messages. These methods, however, are non-blind as they require information about known steganography techniques and are easily bypassed. Recent work has instead focused on a defense mechanism known as sanitization, which eliminates hidden information from images. In this work, we introduce a novel blind deep learning steganography sanitization method that utilizes a diffusion model framework to sanitize universal and dependent steganography (DM-SUDS), which both sanitizes and preserves image quality. We evaluate this approach against state-of-the-art deep learning sanitization frameworks and provide further detailed analysis through an ablation study. DM-SUDS outperforms previous sanitization methods and improves image preservation MSE by 71.32%, PSNR by 22.43% and SSIM by 17.30%. This is the first blind deep learning image sanitization framework to meet these image quality results.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (35)
  1. Optimal image steganography content destruction techniques. In International Conference on Systems, Control, Signal Processing and Informatics, pp.  453–457, 2013.
  2. Anti-forensic approach to remove stego content from images and videos. Journal of Cyber Security and Mobility, pp.  295–320, 2019.
  3. Image steganography and steganalysis. Wiley Interdisciplinary Reviews: Computational Statistics, 3(3):251–259, 2011.
  4. Shumeet Baluja. Hiding images in plain sight: Deep steganography. Advances in neural information processing systems, 30, 2017. https://papers.nips.cc/paper/2017/file/838e8afb1ca34354ac209f53d90c3a43-Paper.pdf.
  5. Digital image steganography: Survey and analysis of current methods. Signal processing, 90(3):727–752, 2010. https://www.sciencedirect.com/science/article/abs/pii/S0165168409003648.
  6. Destruction of image steganography using generative adversarial networks. arXiv preprint arXiv:1912.10070, 2019.
  7. Steganogram removal using multidirectional diffusion in fourier domain while preserving perceptual image quality. Pattern Recognition Letters, 147:197–205, 2021.
  8. Generating steganographic images via adversarial training. Advances in neural information processing systems, 30, 2017.
  9. Exploring steganography: Seeing the unseen. Computer, 31(2):26–34, 1998a. doi: 10.1109/MC.1998.4655281. URL https://ieeexplore.ieee.org/document/4655281. https://ieeexplore.ieee.org/document/4655281.
  10. Steganalysis of images created using current steganography software. In International Workshop on Information Hiding, pp.  273–289. Springer, 1998b.
  11. Pixelsteganalysis: Pixel-wise hidden information removal with low visual degradation. IEEE Transactions on Dependable and Secure Computing, 2021.
  12. A review on steganography through multimedia. In 2016 International Conference on Research Advances in Integrated Navigation Systems (RAINS), pp.  1–6. IEEE, 2016. https://ieeexplore.ieee.org/document/7764373.
  13. C. Kurak and J. McHugh. A cautionary note on image downgrading. In [1992] Proceedings Eighth Annual Computer Security Application Conference, pp.  153–159, 1992. doi: 10.1109/CSAC.1992.228224. https://ieeexplore.ieee.org/document/228224.
  14. Ensemble stego selection for enhancing image steganography. IEEE Signal Processing Letters, 29:702–706, 2022.
  15. Improved denoising diffusion probabilistic models. In International Conference on Machine Learning, pp.  8162–8171. PMLR, 2021.
  16. Image sterilization to prevent lsb-based steganographic transmission. arXiv preprint arXiv:1012.5573, 2010.
  17. Feature learning for steganalysis using convolutional neural networks. Multimedia Tools and Applications, 77:19633–19657, 2018.
  18. Suds: Sanitizing universal and dependent steganography. European Conference on Artificial Intelligence, 2023. https://arxiv.org/abs/2309.13467.
  19. Current status and key issues in image steganography: A survey. Computer science review, 13:95–113, 2014. https://www.sciencedirect.com/science/article/abs/pii/S1574013714000136.
  20. Automatic steganographic distortion learning using a generative adversarial network. IEEE Signal Processing Letters, 24(10):1547–1551, 2017. https://ieeexplore.ieee.org/document/8017430.
  21. Cnn-based adversarial embedding for image steganography. IEEE Transactions on Information Forensics and Security, 14(8):2074–2087, 2019.
  22. An automatic cost learning framework for image steganography using deep reinforcement learning. IEEE Transactions on Information Forensics and Security, 16:952–967, 2020. https://ieeexplore.ieee.org/document/9205850.
  23. Analysis of several image steganography techniques in spatial domain: A survey. In Proceedings of the Second International Conference on Information and Communication Technology for Competitive Strategies, pp.  1–7, 2016. https://dl.acm.org/doi/10.1145/2905055.2905294.
  24. Steganographic generative adversarial networks. In Twelfth international conference on machine vision (ICMV 2019), volume 11433, pp.  991–1005. SPIE, 2020. https://doi.org/10.1117/12.2559429.
  25. Sstegan: Self-learning steganography based on generative adversarial networks. In International Conference on Neural Information Processing, pp.  253–264. Springer, 2018. https://link.springer.com/chapter/10.1007/978-3-030-04179-3_22.
  26. Gan-based steganography with the concatenation of multiple feature maps. In International Workshop on Digital Watermarking, pp.  3–17. Springer, 2020. https://link.springer.com/chapter/10.1007/978-3-030-43575-2_1.
  27. Guanshuo Xu. Deep convolutional neural network to detect j-uniward. In Proceedings of the 5th ACM workshop on information hiding and multimedia security, pp.  67–73, 2017.
  28. Structural design of convolutional neural networks for steganalysis. IEEE Signal Processing Letters, 23(5):708–712, 2016.
  29. An embedding cost learning framework using gan. IEEE Transactions on Information Forensics and Security, 15:839–851, 2019. https://ieeexplore.ieee.org/abstract/document/8735922.
  30. Deep learning hierarchical representations for image steganalysis. IEEE Transactions on Information Forensics and Security, 12(11):2545–2557, 2017.
  31. Udh: Universal deep hiding for steganography, watermarking, and light field messaging. Advances in Neural Information Processing Systems, 33:10223–10234, 2020. https://proceedings.neurips.cc/paper/2020/file/73d02e4344f71a0b0d51a925246990e7-Paper.pdf.
  32. Efficient feature learning and multi-size image steganalysis based on cnn. arXiv preprint arXiv:1807.11428, 2018.
  33. Hidden: Hiding data with deep networks. In Proceedings of the European conference on computer vision (ECCV), pp.  657–672, 2018. https://link.springer.com/chapter/10.1007/978-3-030-01267-0_40.
  34. Destroying robust steganography in online social networks. Information Sciences, 581:605–619, 2021.
  35. Sanitization of images containing stegomalware via machine learning approaches. In ITASEC, 2021. https://ceur-ws.org/Vol-2940/paper31.pdf.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now