Differentially Private Bayesian Programming
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...
Gespeichert in:
| Veröffentlicht in: | arXiv.org 2016-08 |
|---|---|
| Hauptverfasser: | , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | arXiv.org |
| container_volume | |
| creator | Barthe, Gilles Farina, Gian Pietro Gaboardi, Marco Emilio Jesùs Gallego Arias Gordon, Andy Hsu, Justin Strub, Pierre-Yves |
| description | 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. |
| doi_str_mv | 10.48550/arxiv.1605.00283 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_1605_00283</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2071779924</sourcerecordid><originalsourceid>FETCH-LOGICAL-a524-519777d5112916066b706fa8f0a21cdafe478b9e52d889594f98365662d35f573</originalsourceid><addsrcrecordid>eNotj0tLAzEUhYMgWGp_gCsLLmXG5CY3j6VWq0JBF90Pt05SUuZRM9Pi_HvH1tWBj8PhfIzdCJ4ri8gfKP3EYy40x5xzsPKCTUBKkVkFcMVmXbfjI9cGEOWE3T_HEHzyTR-pqob5Z4pH6v38iQbfRWpG0G4T1XVsttfsMlDV-dl_Ttl6-bJevGWrj9f3xeMqIwSVoXDGmBKFADe-0HpjuA5kAycQXyUFr4zdOI9QWuvQqeCs1Kg1lBIDGjllt-fZk0mxT7GmNBR_RsXJaGzcnRv71H4ffNcXu_aQmvFTAdwIY5wDJX8BsAhMBQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2071779924</pqid></control><display><type>article</type><title>Differentially Private Bayesian Programming</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Barthe, Gilles ; Farina, Gian Pietro ; Gaboardi, Marco ; Emilio Jesùs Gallego Arias ; Gordon, Andy ; Hsu, Justin ; Strub, Pierre-Yves</creator><creatorcontrib>Barthe, Gilles ; Farina, Gian Pietro ; Gaboardi, Marco ; Emilio Jesùs Gallego Arias ; Gordon, Andy ; Hsu, Justin ; Strub, Pierre-Yves</creatorcontrib><description>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.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.1605.00283</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Algorithms ; Bayesian analysis ; Computer Science - Programming Languages ; Machine learning ; Privacy ; Probabilistic inference ; Programming languages ; Statistical analysis ; Statistical inference</subject><ispartof>arXiv.org, 2016-08</ispartof><rights>2016. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,784,885,27925</link.rule.ids><backlink>$$Uhttps://doi.org/10.48550/arXiv.1605.00283$$DView paper in arXiv$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.1145/2976749.2978371$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink></links><search><creatorcontrib>Barthe, Gilles</creatorcontrib><creatorcontrib>Farina, Gian Pietro</creatorcontrib><creatorcontrib>Gaboardi, Marco</creatorcontrib><creatorcontrib>Emilio Jesùs Gallego Arias</creatorcontrib><creatorcontrib>Gordon, Andy</creatorcontrib><creatorcontrib>Hsu, Justin</creatorcontrib><creatorcontrib>Strub, Pierre-Yves</creatorcontrib><title>Differentially Private Bayesian Programming</title><title>arXiv.org</title><description>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.</description><subject>Algorithms</subject><subject>Bayesian analysis</subject><subject>Computer Science - Programming Languages</subject><subject>Machine learning</subject><subject>Privacy</subject><subject>Probabilistic inference</subject><subject>Programming languages</subject><subject>Statistical analysis</subject><subject>Statistical inference</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2016</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GOX</sourceid><recordid>eNotj0tLAzEUhYMgWGp_gCsLLmXG5CY3j6VWq0JBF90Pt05SUuZRM9Pi_HvH1tWBj8PhfIzdCJ4ri8gfKP3EYy40x5xzsPKCTUBKkVkFcMVmXbfjI9cGEOWE3T_HEHzyTR-pqob5Z4pH6v38iQbfRWpG0G4T1XVsttfsMlDV-dl_Ttl6-bJevGWrj9f3xeMqIwSVoXDGmBKFADe-0HpjuA5kAycQXyUFr4zdOI9QWuvQqeCs1Kg1lBIDGjllt-fZk0mxT7GmNBR_RsXJaGzcnRv71H4ffNcXu_aQmvFTAdwIY5wDJX8BsAhMBQ</recordid><startdate>20160817</startdate><enddate>20160817</enddate><creator>Barthe, Gilles</creator><creator>Farina, Gian Pietro</creator><creator>Gaboardi, Marco</creator><creator>Emilio Jesùs Gallego Arias</creator><creator>Gordon, Andy</creator><creator>Hsu, Justin</creator><creator>Strub, Pierre-Yves</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20160817</creationdate><title>Differentially Private Bayesian Programming</title><author>Barthe, Gilles ; Farina, Gian Pietro ; Gaboardi, Marco ; Emilio Jesùs Gallego Arias ; Gordon, Andy ; Hsu, Justin ; Strub, Pierre-Yves</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a524-519777d5112916066b706fa8f0a21cdafe478b9e52d889594f98365662d35f573</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2016</creationdate><topic>Algorithms</topic><topic>Bayesian analysis</topic><topic>Computer Science - Programming Languages</topic><topic>Machine learning</topic><topic>Privacy</topic><topic>Probabilistic inference</topic><topic>Programming languages</topic><topic>Statistical analysis</topic><topic>Statistical inference</topic><toplevel>online_resources</toplevel><creatorcontrib>Barthe, Gilles</creatorcontrib><creatorcontrib>Farina, Gian Pietro</creatorcontrib><creatorcontrib>Gaboardi, Marco</creatorcontrib><creatorcontrib>Emilio Jesùs Gallego Arias</creatorcontrib><creatorcontrib>Gordon, Andy</creatorcontrib><creatorcontrib>Hsu, Justin</creatorcontrib><creatorcontrib>Strub, Pierre-Yves</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><collection>arXiv Computer Science</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Barthe, Gilles</au><au>Farina, Gian Pietro</au><au>Gaboardi, Marco</au><au>Emilio Jesùs Gallego Arias</au><au>Gordon, Andy</au><au>Hsu, Justin</au><au>Strub, Pierre-Yves</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Differentially Private Bayesian Programming</atitle><jtitle>arXiv.org</jtitle><date>2016-08-17</date><risdate>2016</risdate><eissn>2331-8422</eissn><abstract>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.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.1605.00283</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | EISSN: 2331-8422 |
| ispartof | arXiv.org, 2016-08 |
| issn | 2331-8422 |
| language | eng |
| recordid | cdi_arxiv_primary_1605_00283 |
| source | arXiv.org; Free E- Journals |
| subjects | Algorithms Bayesian analysis Computer Science - Programming Languages Machine learning Privacy Probabilistic inference Programming languages Statistical analysis Statistical inference |
| title | Differentially Private Bayesian Programming |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T22%3A59%3A45IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Differentially%20Private%20Bayesian%20Programming&rft.jtitle=arXiv.org&rft.au=Barthe,%20Gilles&rft.date=2016-08-17&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.1605.00283&rft_dat=%3Cproquest_arxiv%3E2071779924%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2071779924&rft_id=info:pmid/&rfr_iscdi=true |