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] 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
[3] Sensitive Disclosures under Differential Privacy Guarantees
Han, Chao
Wang, Ke
2015 IEEE INTERNATIONAL CONGRESS ON BIG DATA - BIGDATA CONGRESS 2015, 2015, : 110 - 117
[4] 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
[5] Understanding Online Privacy-A Systematic Review of Privacy Visualizations and Privacy by Design Guidelines
Barth, Susanne
Ionita, Dan
Hartel, Pieter
ACM COMPUTING SURVEYS, 2023, 55 (03)
[6] 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,
[7] Differential Privacy meets Verifiable Computation: Achieving Strong Privacy and Integrity Guarantees
Tsaloli, Georgia
Mitrokotsa, Aikaterini
PROCEEDINGS OF THE 16TH INTERNATIONAL JOINT CONFERENCE ON E-BUSINESS AND TELECOMMUNICATIONS, VOL 2: SECRYPT, 2019, : 425 - 430
[8] ProGAP: Progressive Graph Neural Networks with Differential Privacy Guarantees
Sajadmanesh, Sina
Gatica-Perez, Daniel
PROCEEDINGS OF THE 17TH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING, WSDM 2024, 2024, : 596 - 605
[9] Publishing Social Graphs with Differential Privacy Guarantees Based on wPINQ
Li Xiaoye
Yang Jing
Sun Zhenlong
Zhang Jianpei
CHINESE JOURNAL OF ELECTRONICS, 2019, 28 (02) : 273 - 279
[10] DEMO: PrivacyBuDe: Privacy Buckets Demo Tight Differential Privacy Guarantees made Simple
Sommer, David
Meiser, Sebastian
Mohammadi, Esfandiar
PROCEEDINGS OF THE 2018 ACM SIGSAC CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY (CCS'18), 2018, : 2192 - 2194

← 1 2 3 4 5 →