Papers
Topics
Authors
Recent
Search
2000 character limit reached

Sanitizing Hidden Information with Diffusion Models

Published 10 Oct 2023 in cs.CR | (2310.06951v2)

Abstract: Information hiding is the process of embedding data within another form of data, often to conceal its existence or prevent unauthorized access. This process is commonly used in various forms of secure communications (steganography) that can be used by bad actors to propagate malware, exfiltrate victim data, and discreetly communicate. Recent work has utilized deep neural networks to remove this hidden information in a defense mechanism known as sanitization. Previous deep learning works, however, are unable to scale efficiently beyond the MNIST dataset. In this work, we present a novel sanitization method called DM-SUDS that utilizes a diffusion model framework to sanitize/remove hidden information from image-into-image universal and dependent steganography from CIFAR-10 and ImageNet datasets. We evaluate DM-SUDS against three different baselines using MSE, PSNR, SSIM, and NCC metrics and provide further detailed analysis through an ablation study. DM-SUDS outperforms all three baselines and significantly improves image preservation MSE by 50.44%, PSNR by 12.69%, SSIM by 11.49%, and NCC by 3.26% compared to previous deep learning approaches. Additionally, we introduce a novel evaluation specification that considers the successful removal of hidden information (safety) as well as the resulting quality of the sanitized image (utility). We further demonstrate the versatility of this method with an application in an audio case study, demonstrating its broad applicability to additional domains.

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

No one has generated a summary of this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Summarize

Paper to Video (Beta)

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

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

Continue Learning

We haven't generated follow-up questions for this paper yet.

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

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up