Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

DPGOMI: Differentially Private Data Publishing with Gaussian Optimized Model Inversion (2310.04528v1)

Published 6 Oct 2023 in cs.LG

Abstract: High-dimensional data are widely used in the era of deep learning with numerous applications. However, certain data which has sensitive information are not allowed to be shared without privacy protection. In this paper, we propose a novel differentially private data releasing method called Differentially Private Data Publishing with Gaussian Optimized Model Inversion (DPGOMI) to address this issue. Our approach involves mapping private data to the latent space using a public generator, followed by a lower-dimensional DP-GAN with better convergence properties. We evaluate the performance of DPGOMI on standard datasets CIFAR10 and SVHN. Our results show that DPGOMI outperforms the standard DP-GAN method in terms of Inception Score, Fr\'echet Inception Distance, and classification performance, while providing the same level of privacy. Our proposed approach offers a promising solution for protecting sensitive data in GAN training while maintaining high-quality results.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (19)
  1. M. Abadi, A. Chu, I. Goodfellow, H. B. McMahan, I. Mironov, K. Talwar, and L. Zhang, “Deep learning with differential privacy,” in Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, 2016, pp. 308–318.
  2. Z. Bu, H. Wang, Q. Long, and W. J. Su, “On the convergence of deep learning with differential privacy,” arXiv e-prints, pp. arXiv–2106, 2021.
  3. D. Chen, S.-c. S. Cheung, C.-N. Chuah, and S. Ozonoff, “Differentially private generative adversarial networks with model inversion,” in 2021 IEEE International Workshop on Information Forensics and Security (WIFS).   IEEE, 2021, pp. 1–6.
  4. A. Krizhevsky, G. Hinton et al., “Learning multiple layers of features from tiny images,” 2009.
  5. Y. Netzer, T. Wang, A. Coates, A. Bissacco, B. Wu, and A. Y. Ng, “Reading digits in natural images with unsupervised feature learning,” 2011.
  6. C. Dwork, A. Roth et al., “The algorithmic foundations of differential privacy.” Foundations and Trends in Theoretical Computer Science, vol. 9, no. 3-4, pp. 211–407, 2014.
  7. N. Papernot, S. Song, I. Mironov, A. Raghunathan, K. Talwar, and U. Erlingsson, “Scalable Private Learning with PATE,” in International Conference on Learning Representations, 2018.
  8. F. Harder, M. Jalali, D. J. Sutherland, and M. Park, “Pre-trained perceptual features improve differentially private image generation,” Transactions on Machine Learning Research, 2023.
  9. L. Fan, “A survey of differentially private generative adversarial networks,” in The AAAI Workshop on Privacy-Preserving Artificial Intelligence, 2020.
  10. D. Chen, T. Orekondy, and M. Fritz, “GS-WGAN: A gradient-sanitized approach for learning differentially private generators,” Advances in Neural Information Processing Systems, vol. 33, 2020.
  11. J. Jordon, J. Yoon, and M. van der Schaar, “PATE-GAN: Generating synthetic data with differential privacy guarantees,” in International Conference on Learning Representations, 2018.
  12. Y. Long, B. Wang, Z. Yang, B. Kailkhura, A. Zhang, C. Gunter, and B. Li, “G-PATE: scalable differentially private data generator via private aggregation of teacher discriminators,” Advances in Neural Information Processing Systems, vol. 34, pp. 2965–2977, 2021.
  13. C. N. d. Santos, Y. Mroueh, I. Padhi, and P. Dognin, “Learning implicit generative models by matching perceptual features,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 4461–4470.
  14. F. Harder, K. Adamczewski, and M. Park, “DP-MERF: Differentially private mean embeddings with randomfeatures for practical privacy-preserving data generation,” in International conference on artificial intelligence and statistics.   PMLR, 2021, pp. 1819–1827.
  15. I. Mironov, “Rényi differential privacy,” in 2017 IEEE 30th Computer Security Foundations Symposium (CSF).   IEEE, 2017, pp. 263–275.
  16. M. Arjovsky, S. Chintala, and L. Bottou, “Wasserstein GAN,” arXiv preprint arXiv:1701.07875, 2017.
  17. M. Marchesi, “Megapixel size image creation using generative adversarial networks,” arXiv preprint arXiv:1706.00082, 2017.
  18. L. Xie, K. Lin, S. Wang, F. Wang, and J. Zhou, “Differentially private generative adversarial network,” arXiv preprint arXiv:1802.06739, 2018.
  19. A. Borji, “Pros and Cons of GAN evaluation measures: New developments,” arXiv preprint arXiv:2103.09396, 2021.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Dongjie Chen (6 papers)
  2. Sen-ching S. Cheung (1 paper)
  3. Chen-Nee Chuah (19 papers)

Summary

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

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