Differentially Private Bayesian Programming

被引：20

作者：

Barthe, Gilles ^{[1
]}

Farina, Gian Pietro ^{[2
]}

Gaboardi, Marco ^{[2
]}

Arias, Emilio Jesus Gallego ^{[3
]}

Gordon, Andy ^{[4
]}

Hsu, Justin ^{[5
]}

Strub, Pierre-Yves ^{[1
]}

机构：

[1] IMDEA Software, Madrid, Spain

[2] Univ Buffalo, Buffalo, NY USA

[3] CRI Mines ParisTech, Fontainebleau, France

[4] Microsoft Res, Cambridge, England

[5] Univ Penn, Philadelphia, PA 19104 USA

来源：

CCS'16: PROCEEDINGS OF THE 2016 ACM SIGSAC CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY | 2016年

关键词：

D O I：

10.1145/2976749.2978371

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

We present PrivInfer, an expressive framework for writing and verifying differentially private Bayesian machine learning algorithms. Programs in PrivInfer are written in a rich functional probabilistic programming language with constructs for performing Bayesian inference. Then, differential privacy of programs is established using a relational refinement type system, in which refinements on probability types are indexed by a metric on distributions. Our framework leverages recent developments in Bayesian inference, probabilistic programming languages, and in relational refinement types. We demonstrate the expressiveness of PrivInfer by verifying privacy for several examples of private Bayesian inference.

引用

页码：68 / 79

页数：12

共 50 条

[1] Differentially Private Bayesian Optimization
Kusner, Matt J.
Gardner, Jacob R.
Garnett, Roman
Weinberger, Kilian Q.
[J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 37, 2015, 37 : 918 - 927
[2] Differentially Private Bayesian Linear Regression
Bernstein, Garrett
Sheldon, Daniel
[J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32
[3] On Differentially Private Inductive Logic Programming
Zeng, Chen
Lantz, Eric
Naughton, Jeffrey F.
Page, David
[J]. INDUCTIVE LOGIC PROGRAMMING: 23RD INTERNATIONAL CONFERENCE, 2014, 8812 : 18 - 30
[4] Differentially Private Bayesian Inference for Exponential Families
Bernstein, Garrett
Sheldon, Daniel
[J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31
[5] Differentially private Bayesian learning on distributed data
Heikkila, Mikko
Lagerspetz, Eemil
Kaski, Samuel
Shimizu, Kana
Tarkoma, Sasu
Honkela, Antti
[J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017), 2017, 30
[6] Statistic selection and MCMC for differentially private Bayesian estimation
Barış Alparslan
Sinan Yıldırım
[J]. Statistics and Computing, 2022, 32
[7] Differentially private online Bayesian estimation with adaptive truncation
Yildirim, Sinan
[J]. TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES, 2024, 32 (01) : 34 - 50
[8] Statistic selection and MCMC for differentially private Bayesian estimation
Alparslan, Baris
Yildirim, Sinan
[J]. STATISTICS AND COMPUTING, 2022, 32 (05)
[9] Differentially Private Distributed Bayesian Linear Regression with MCMC
Alparslan, Baris
Yildirim, Sinan
Birbil, S. Ilker
[J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 202, 2023, 202 : 627 - 641
[10] Differentially Private Bayesian Inference for Generalized Linear Models
Kulkarni, Tejas
Jalko, Joonas
Koskela, Antti
Kaski, Samuel
Honkela, Antti
[J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, 2021, 139

← 1 2 3 4 5 →