Skip to main content

Context-Aware Generative Adversarial Privacy

Abstract Preserving the utility of published datasets while simultaneously providing provable privacy guarantees is a well-known challenge. On the one hand, context-free privacy solutions, such as differential privacy, provide strong privacy guarantees, but often lead to a significant reduction in utility. On the other hand, context-aware privacy solutions, such as information theoretic privacy, achieve an improved privacy-utility tradeoff, but assume that the data holder has access to dataset statistics. We circumvent these limitations by introducing a novel context-aware privacy framework called generative adversarial privacy (GAP). GAP leverages recent advancements in generative adversarial networks (GANs) to allow the data holder to learn privat... (more)
Created Date 2017-12-01
Contributor Huang, Chong (ASU author) / Kairouz, Peter (Author) / Chen, Xiao (Author) / Sankar, Lalitha (ASU author) / Rajagopal, Ram (Author) / Ira A. Fulton Schools of Engineering / School of Electrical, Computer and Energy Engineering
Type Text
Extent 35 pages
Language English
Identifier DOI: 10.3390/e19120656 / ISSN: 1099-4300
Reuse Permissions
Citation Huang, C., Kairouz, P., Chen, X., Sankar, L., & Rajagopal, R. (2017). Context-Aware Generative Adversarial Privacy. Entropy, 19(12), 656. doi:10.3390/e19120656
Collaborating Institutions ASU Library
Additional Formats MODS / OAI Dublin Core / RIS

  Context-Aware Generative_2017.pdf
2.3 MB application/pdf
Download Count: 135