Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
167 tokens/sec
GPT-4o
7 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

MedBlindTuner: Towards Privacy-preserving Fine-tuning on Biomedical Images with Transformers and Fully Homomorphic Encryption (2401.09604v1)

Published 17 Jan 2024 in cs.CR, cs.CV, and cs.LG

Abstract: Advancements in ML have significantly revolutionized medical image analysis, prompting hospitals to rely on external ML services. However, the exchange of sensitive patient data, such as chest X-rays, poses inherent privacy risks when shared with third parties. Addressing this concern, we propose MedBlindTuner, a privacy-preserving framework leveraging fully homomorphic encryption (FHE) and a data-efficient image transformer (DEiT). MedBlindTuner enables the training of ML models exclusively on FHE-encrypted medical images. Our experimental evaluation demonstrates that MedBlindTuner achieves comparable accuracy to models trained on non-encrypted images, offering a secure solution for outsourcing ML computations while preserving patient data privacy. To the best of our knowledge, this is the first work that uses data-efficient image transformers and fully homomorphic encryption in this domain.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (39)
  1. Recognition of peripheral blood cell images using convolutional neural networks. Computer methods and programs in biomedicine, 180: 105020.
  2. A dataset of microscopic peripheral blood cell images for development of automatic recognition systems. Data in brief, 30.
  3. The liver tumor segmentation benchmark (lits). Medical Image Analysis, 84: 102680.
  4. (Leveled) fully homomorphic encryption without bootstrapping. ACM Transactions on Computation Theory (TOCT), 6(3): 1–36.
  5. Bootstrapping for approximate homomorphic encryption. In Advances in Cryptology–EUROCRYPT 2018: 37th Annual International Conference on the Theory and Applications of Cryptographic Techniques, Tel Aviv, Israel, April 29-May 3, 2018 Proceedings, Part I 37, 360–384. Springer.
  6. Homomorphic encryption for arithmetic of approximate numbers. In Advances in Cryptology–ASIACRYPT 2017: 23rd International Conference on the Theory and Applications of Cryptology and Information Security, Hong Kong, China, December 3-7, 2017, Proceedings, Part I 23, 409–437. Springer.
  7. Practical FHE parameters against lattice attacks. Cryptology ePrint Archive.
  8. Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration (isic). arXiv preprint arXiv:1902.03368.
  9. Creeger, M. 2022. The Rise of Fully Homomorphic Encryption: Often called the Holy Grail of cryptography, commercial FHE is near. Queue, 20(4): 39–60.
  10. Crockett, E. 2020. A low-depth homomorphic circuit for logistic regression model training. Cryptology ePrint Archive.
  11. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, 248–255. Ieee.
  12. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.
  13. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929.
  14. Gentry, C. 2009. A fully homomorphic encryption scheme. Stanford university.
  15. Cryptonets: Applying neural networks to encrypted data with high throughput and accuracy. In International conference on machine learning, 201–210. PMLR.
  16. ML confidential: Machine learning on encrypted data. In International Conference on Information Security and Cryptology, 1–21. Springer.
  17. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, 770–778.
  18. Privacy-preserving machine learning as a service. Proc. Priv. Enhancing Technol., 2018(3): 123–142.
  19. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11): 2278–2324.
  20. HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic Encryption.
  21. When machine learning meets privacy: A survey and outlook. ACM Computing Surveys (CSUR), 54(2): 1–36.
  22. Glyph: Fast and accurately training deep neural networks on encrypted data. Advances in neural information processing systems, 33: 9193–9202.
  23. Secureml: A system for scalable privacy-preserving machine learning. In 2017 IEEE Symposium on Security and Privacy (SP), 19–38. IEEE.
  24. Towards deep neural network training on encrypted data. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops, 0–0.
  25. Nesterov, Y. E. 1983. A method of solving a convex programming problem with convergence rate O\\\backslash\bigl(k^2\\\backslash\bigr). In Doklady Akademii Nauk, volume 269, 543–547. Russian Academy of Sciences.
  26. A survey on transfer learning. IEEE Transactions on knowledge and data engineering, 22(10): 1345–1359.
  27. Cheetah: Optimizing and accelerating homomorphic encryption for private inference. In 2021 IEEE International Symposium on High-Performance Computer Architecture (HPCA), 26–39. IEEE.
  28. Vision Transformer for Efficient Chest X-ray and Gastrointestinal Image Classification. arXiv preprint arXiv:2304.11529.
  29. Mlaas: Machine learning as a service. In 2015 IEEE 14th international conference on machine learning and applications (ICMLA), 896–902. IEEE.
  30. Deepsecure: Scalable provably-secure deep learning. In Proceedings of the 55th Annual Design Automation Conference, 1–6.
  31. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
  32. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning, 6105–6114. PMLR.
  33. Training data-efficient image transformers & distillation through attention. In International conference on machine learning, 10347–10357. PMLR.
  34. Tschandl, P. 2018. The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions.
  35. The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Scientific data, 5(1): 1–9.
  36. Attention is all you need. Advances in neural information processing systems, 30.
  37. Securenn: 3-party secure computation for neural network training. Proceedings on Privacy Enhancing Technologies, 2019(3): 26–49.
  38. A survey of transfer learning. Journal of Big data, 3(1): 1–40.
  39. MedMNIST v2-A large-scale lightweight benchmark for 2D and 3D biomedical image classification. Scientific Data, 10(1): 41.

Summary

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

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

Tweets