Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
162 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 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

Privacy-Preserving Deep Learning Using Deformable Operators for Secure Task Learning (2404.05828v1)

Published 8 Apr 2024 in cs.CV, cs.CR, and eess.IV

Abstract: In the era of cloud computing and data-driven applications, it is crucial to protect sensitive information to maintain data privacy, ensuring truly reliable systems. As a result, preserving privacy in deep learning systems has become a critical concern. Existing methods for privacy preservation rely on image encryption or perceptual transformation approaches. However, they often suffer from reduced task performance and high computational costs. To address these challenges, we propose a novel Privacy-Preserving framework that uses a set of deformable operators for secure task learning. Our method involves shuffling pixels during the analog-to-digital conversion process to generate visually protected data. Those are then fed into a well-known network enhanced with deformable operators. Using our approach, users can achieve equivalent performance to original images without additional training using a secret key. Moreover, our method enables access control against unauthorized users. Experimental results demonstrate the efficacy of our approach, showcasing its potential in cloud-based scenarios and privacy-sensitive applications.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (20)
  1. “Privacy-preserving deep learning on machine learning as a service—a comprehensive survey,” IEEE Access, vol. 8, pp. 167425–167447, 2020.
  2. “Survey on securing data storage in the cloud,” APSIPA Transactions on Signal and Information Processing, vol. 3, pp. e7, 2014.
  3. “A privacy-preserving distributed architecture for deep-learning-as-a-service,” in 2020 International Joint Conference on Neural Networks (IJCNN). IEEE, 2020, pp. 1–8.
  4. “Optimized privacy-preserving cnn inference with fully homomorphic encryption,” IEEE Transactions on Information Forensics and Security, vol. 18, pp. 2175–2187, 2023.
  5. “An overview of compressible and learnable image transformation with secret key and its applications,” APSIPA Transactions on Signal and Information Processing, vol. 11, no. 1, 2022.
  6. Masayuki Tanaka, “Learnable image encryption,” CoRR, vol. abs/1804.00490, 2018.
  7. “Block-wise scrambled image recognition using adaptation network,” arXiv preprint arXiv:2001.07761, 2020.
  8. “Privacy-preserving image classification using convmixer with adaptative permutation matrix and block-wise scrambled image encryption,” Journal of Imaging, vol. 9, no. 4, pp. 85, 2023.
  9. “Privacy-preserving image classification using vision transformer,” in 2022 30th European Signal Processing Conference (EUSIPCO). IEEE, 2022, pp. 543–547.
  10. “Image to perturbation: An image transformation network for generating visually protected images for privacy-preserving deep neural networks,” IEEE Access, vol. 9, pp. 64629–64638, 2021.
  11. “A gan-based image transformation scheme for privacy-preserving deep neural networks,” in 2020 28th European Signal Processing Conference (EUSIPCO). IEEE, 2021, pp. 745–749.
  12. “End-to-end optimization of optics and image processing for achromatic extended depth of field and super-resolution imaging,” ACM Transactions on Graphics (TOG), vol. 37, no. 4, pp. 1–13, 2018.
  13. “Optics lens design for privacy-preserving scene captioning,” in 2022 IEEE International Conference on Image Processing (ICIP). IEEE, 2022, pp. 3551–3555.
  14. “Key-nets: Optical transformation convolutional networks for privacy preserving vision sensors,” arXiv preprint arXiv:2008.04469, 2020.
  15. “Deformable convolutional networks,” in Proceedings of the IEEE international conference on computer vision, 2017, pp. 764–773.
  16. “Access control using spatially invariant permutation of feature maps for semantic segmentation models,” in 2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). IEEE, 2021, pp. 1833–1838.
  17. “Very deep convolutional networks for large-scale image recognition,” arXiv preprint arXiv:1409.1556, 2014.
  18. “Identity mappings in deep residual networks,” in Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part IV 14. Springer, 2016, pp. 630–645.
  19. “Encryption-then-compression systems using grayscale-based image encryption for jpeg images,” IEEE Transactions on Information Forensics and security, vol. 14, no. 6, pp. 1515–1525, 2018.
  20. “Fully convolutional networks for semantic segmentation,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 3431–3440.

Summary

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