Natural differential privacy-a perspective on protection guarantees

被引：0

作者：

Altman, Micah ^{[1
]}

Cohen, Aloni ^{[2
]}

机构：

[1] MIT, MIT Lib, CREOS, Cambridge, MA 02139 USA

[2] Univ Chicago, Comp Sci, Chicago, IL USA

来源：

PEERJ COMPUTER SCIENCE | 2023年 / 9卷

关键词：

Differential privacy; Physical mechanisms; No free lunch; Privacy by design; Privacy by default;

D O I：

10.7717/peerj-cs.1576

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We introduce "Natural" differential privacy (NDP)-which utilizes features of existing hardware architecture to implement differentially private computations. We show that NDP both guarantees strong bounds on privacy loss and constitutes a practical exception to no-free-lunch theorems on privacy. We describe how NDP can be efficiently implemented and how it aligns with recognized privacy principles and frameworks. We discuss the importance of formal protection guarantees and the relationship between formal and substantive protections.

引用

页数：11

共 50 条

[1] Natural differential privacy—a perspective on protection guarantees
Altman M.
Cohen A.
PeerJ Computer Science, 2023, 9
[2] Pairwise Learning with Differential Privacy Guarantees
Huai, Mengdi
Wang, Di
Miao, Chenglin
Xu, Jinhui
Zhang, Aidong
THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 694 - 701
[3] Individual Differential Privacy: A Utility-Preserving Formulation of Differential Privacy Guarantees
Soria-Comas, Jordi
Domingo-Ferrer, Josep
Sanchez, David
Megias, David
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2017, 12 (06) : 1418 - 1429
[4] The Politics of Privacy-A Useful Tautology
Moeller, Johanna E.
Nowak, Jakub
Kannengiesser, Sigrid
Moeller, Judith E.
MEDIA AND COMMUNICATION, 2020, 8 (02): : 232 - 236
[5] Sensitive Disclosures under Differential Privacy Guarantees
Han, Chao
Wang, Ke
2015 IEEE INTERNATIONAL CONGRESS ON BIG DATA - BIGDATA CONGRESS 2015, 2015, : 110 - 117
[6] PERSONAL PRIVACY-A CASE OF HIGH POLICY
WEBBER, EW
PUBLIC ADMINISTRATION REVIEW, 1960, 20 (03) : 158 - 160
[7] Computing Tight Differential Privacy Guarantees Using FFT
Koskela, Antti
Jalko, Joonas
Honkela, Antti
INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 108, 2020, 108 : 2560 - 2568
[8] Laplacian Smoothing Stochastic ADMMs With Differential Privacy Guarantees
Liu, Yuanyuan
Geng, Jiacheng
Shang, Fanhua
An, Weixin
Liu, Hongying
Zhu, Qi
Feng, Wei
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2022, 17 : 1814 - 1826
[9] Personal Voice Assistant Security and Privacy-A Survey
Cheng, Peng
Roedig, Utz
PROCEEDINGS OF THE IEEE, 2022, 110 (04) : 476 - 507
[10] Super-convergence and Differential Privacy: Training faster with better privacy guarantees
Frisk, Osvald
Dormann, Friedrich
Lillelund, Christian Marius
Pedersen, Christian Fischer
2021 55TH ANNUAL CONFERENCE ON INFORMATION SCIENCES AND SYSTEMS (CISS), 2021,

← 1 2 3 4 5 →