Generative Adversarial Privacy. Huang, C., Kairouz, P., Chen, X., Sankar, L., & Rajagopal, R. arXiv:1807.05306 [cs, math, stat], June, 2019. arXiv: 1807.05306![Generative Adversarial Privacy [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper abstract bibtex We present a data-driven framework called generative adversarial privacy (GAP). Inspired by recent advancements in generative adversarial networks (GANs), GAP allows the data holder to learn the privatization mechanism directly from the data. Under GAP, finding the optimal privacy mechanism is formulated as a constrained minimax game between a privatizer and an adversary. We show that for appropriately chosen adversarial loss functions, GAP provides privacy guarantees against strong information-theoretic adversaries. We also evaluate GAP's performance on the GENKI face database.
@article{huang_generative_2019,
title = {Generative {Adversarial} {Privacy}},
url = {http://arxiv.org/abs/1807.05306},
abstract = {We present a data-driven framework called generative adversarial privacy (GAP). Inspired by recent advancements in generative adversarial networks (GANs), GAP allows the data holder to learn the privatization mechanism directly from the data. Under GAP, finding the optimal privacy mechanism is formulated as a constrained minimax game between a privatizer and an adversary. We show that for appropriately chosen adversarial loss functions, GAP provides privacy guarantees against strong information-theoretic adversaries. We also evaluate GAP's performance on the GENKI face database.},
urldate = {2020-09-08},
journal = {arXiv:1807.05306 [cs, math, stat]},
author = {Huang, Chong and Kairouz, Peter and Chen, Xiao and Sankar, Lalitha and Rajagopal, Ram},
month = jun,
year = {2019},
note = {arXiv: 1807.05306},
keywords = {\#broken, Computer Science - Computer Science and Game Theory, Computer Science - Cryptography and Security, Computer Science - Information Theory, Computer Science - Machine Learning, Jab/\#Pre, Statistics - Machine Learning, ⛔ No DOI found},
}
Downloads: 0
{"_id":"2XvYutajFC5ERJb2z","bibbaseid":"huang-kairouz-chen-sankar-rajagopal-generativeadversarialprivacy-2019","author_short":["Huang, C.","Kairouz, P.","Chen, X.","Sankar, L.","Rajagopal, R."],"bibdata":{"bibtype":"article","type":"article","title":"Generative Adversarial Privacy","url":"http://arxiv.org/abs/1807.05306","abstract":"We present a data-driven framework called generative adversarial privacy (GAP). Inspired by recent advancements in generative adversarial networks (GANs), GAP allows the data holder to learn the privatization mechanism directly from the data. Under GAP, finding the optimal privacy mechanism is formulated as a constrained minimax game between a privatizer and an adversary. We show that for appropriately chosen adversarial loss functions, GAP provides privacy guarantees against strong information-theoretic adversaries. We also evaluate GAP's performance on the GENKI face database.","urldate":"2020-09-08","journal":"arXiv:1807.05306 [cs, math, stat]","author":[{"propositions":[],"lastnames":["Huang"],"firstnames":["Chong"],"suffixes":[]},{"propositions":[],"lastnames":["Kairouz"],"firstnames":["Peter"],"suffixes":[]},{"propositions":[],"lastnames":["Chen"],"firstnames":["Xiao"],"suffixes":[]},{"propositions":[],"lastnames":["Sankar"],"firstnames":["Lalitha"],"suffixes":[]},{"propositions":[],"lastnames":["Rajagopal"],"firstnames":["Ram"],"suffixes":[]}],"month":"June","year":"2019","note":"arXiv: 1807.05306","keywords":"#broken, Computer Science - Computer Science and Game Theory, Computer Science - Cryptography and Security, Computer Science - Information Theory, Computer Science - Machine Learning, Jab/#Pre, Statistics - Machine Learning, ⛔ No DOI found","bibtex":"@article{huang_generative_2019,\n\ttitle = {Generative {Adversarial} {Privacy}},\n\turl = {http://arxiv.org/abs/1807.05306},\n\tabstract = {We present a data-driven framework called generative adversarial privacy (GAP). Inspired by recent advancements in generative adversarial networks (GANs), GAP allows the data holder to learn the privatization mechanism directly from the data. Under GAP, finding the optimal privacy mechanism is formulated as a constrained minimax game between a privatizer and an adversary. We show that for appropriately chosen adversarial loss functions, GAP provides privacy guarantees against strong information-theoretic adversaries. We also evaluate GAP's performance on the GENKI face database.},\n\turldate = {2020-09-08},\n\tjournal = {arXiv:1807.05306 [cs, math, stat]},\n\tauthor = {Huang, Chong and Kairouz, Peter and Chen, Xiao and Sankar, Lalitha and Rajagopal, Ram},\n\tmonth = jun,\n\tyear = {2019},\n\tnote = {arXiv: 1807.05306},\n\tkeywords = {\\#broken, Computer Science - Computer Science and Game Theory, Computer Science - Cryptography and Security, Computer Science - Information Theory, Computer Science - Machine Learning, Jab/\\#Pre, Statistics - Machine Learning, ⛔ No DOI found},\n}\n\n\n\n","author_short":["Huang, C.","Kairouz, P.","Chen, X.","Sankar, L.","Rajagopal, R."],"key":"huang_generative_2019","id":"huang_generative_2019","bibbaseid":"huang-kairouz-chen-sankar-rajagopal-generativeadversarialprivacy-2019","role":"author","urls":{"Paper":"http://arxiv.org/abs/1807.05306"},"keyword":["#broken","Computer Science - Computer Science and Game Theory","Computer Science - Cryptography and Security","Computer Science - Information Theory","Computer Science - Machine Learning","Jab/#Pre","Statistics - Machine Learning","⛔ No DOI found"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/bxt101","dataSources":["Wsv2bQ4jPuc7qme8R"],"keywords":["#broken","computer science - computer science and game theory","computer science - cryptography and security","computer science - information theory","computer science - machine learning","jab/#pre","statistics - machine learning","⛔ no doi found"],"search_terms":["generative","adversarial","privacy","huang","kairouz","chen","sankar","rajagopal"],"title":"Generative Adversarial Privacy","year":2019}