Compressive Privacy Generative Adversarial Network
Abstract
Machine learning as a service (MLaaS) has brought much convenience to our daily lives recently. However, the fact that the service is provided through cloud raises privacy leakage issues. In this work we propose the compressive privacy generative adversarial network (CPGAN), a data-driven adversarial learning framework for generating compressing representations that retain utility comparable to state-of-the-art, with the additional feature of defending against reconstruction attack. This is achieved by applying adversarial learning scheme to the design of compression network (privatizer), whose utility/privacy performances are evaluated by the utility classifier and the adversary reconstructor, respectively. Experimental results demonstrate that CPGAN achieves better utility/privacy trade-off in comparison with the previous work, and is applicable to real-world large datasets.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The compressive privacy GAN defends against preimage privacy attacks in machine learning as a service by ensuring that the input data of a service module contains no sensitive information.
“This method defends against preimage privacy attacks in machine learning as a service by ensuring that the input data of a service module contains no sensitive information.”
From Generative AI in medical practice: in-depth exploration of privacy and security challenges (2024) · cites this paper as [34]
The compressive privacy GAN is designed to preprocess private data before the training stage in machine learning as a service scenarios.
“The compressive privacy GAN is designed to preprocess private data before the training stage in machine learning as a service scenarios [34].”
From Generative AI in medical practice: in-depth exploration of privacy and security challenges (2024) · cites this paper as [34]
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · see citing works
Membership Inference Attacks Against Machine Learning Models
Shokri, R., Stronati, M., Song, C., & Shmatikov, V. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.41 · Cited by 4,754 · see citing works
RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response
Erlingsson, Ú., Pihur, V., & Korolova, A. (2014) · Proceedings of the 2014 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2660267.2660348 · Cited by 1,838 · see citing works
f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
Nowozin, S., Cseke, B., & Tomioka, R. (2016) · arXiv · doi:10.48550/arxiv.1606.00709 · Cited by 1,183 · see citing works
Algorithms that remember: model inversion attacks and data protection law
Veale, M., Binns, R., & Edwards, L. (2018) · Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences · doi:10.1098/rsta.2018.0083 · Cited by 278 · see citing works
Privacy-Preserving Adversarial Networks
Tripathy, A., Wang, Y., & Ishwar, P. (2019) · 2019 57th Annual Allerton Conference on Communication, Control, and Computing (Allerton) · doi:10.1109/allerton.2019.8919758 · Cited by 87 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Generative Adversarial Networks: A Survey Toward Private and Secure Applications
Cai, Z., Xiong, Z., Xu, H., Wang, P., Li, W., & Pan, Y. (2022) · ACM Computing Surveys · doi:10.1145/3459992 · Cited by 376 · see citing works
Generative AI in medical practice: in-depth exploration of privacy and security challenges
Chen, Y., & Esmaeilzadeh, P. (2024) · Journal of Medical Internet Research · doi:10.2196/53008 · Cited by 353 · see citing works
“The compressive privacy GAN is designed to preprocess private data before the training stage in machine learning as a service scenarios [34].”
Zhou, N.-R., Zhang, T.-F., Xie, X.-W., & Wu, J.-Y. (2023) · Signal Processing Image Communication · doi:10.1016/j.image.2022.116891 · Cited by 161 · see citing works
Khosravy, M., Nakamura, K., Hirose, Y., Nitta, N., & Babaguchi, N. (2022) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2022.3140687 · Cited by 94 · see citing works
- Authors
- Tseng, B.-W., & Wu, P.-Y.
- Affiliations
- National Taiwan University (TW)
- Venue
- IEEE Transactions on Information Forensics and Security
- Published
- 2020
- Volume
- 15
- Pages
- 2499-2513
- ISSN
- 1556-6013 (ISSN-L)
- 1556-6021
- OpenAlex
- W3003011734
- Cited by
- 48
- References
- 7
- Citations by year
- 2026: 1 · 2025: 6 · 2024: 11 · 2023: 6 · 2022: 13 · 2021: 9 · 2020: 2
- FWCI
- 2.95
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Information Forensics and Security (publishedVersion)
- Funders
- Ministry of Science and Technology, Taiwan (MOST-107-2634-F-002-008-, MOST-108-2634-F-002-005-)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Information Systems › Cloud Data Security Solutions
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Keywords
- generative adversarial networks, machine learning as a service, privacy-utility trade-off, adversarial learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
