Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Deep learning for differential privacy and density estimation
KTH, School of Electrical Engineering and Computer Science (EECS).
2019 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

One of the most promising opportunities for scientists over the last years is the ease in the collection of data and its accessibility. Moreover, due to the proliferation of interdisciplinary fields, there has emerged the opportunity for data collaboration. For some years, though, organizations, companies, and institutions did not examine secure ways to manage, process, and share data. As a result, we can see nowadays the repercussions of these actions, as some of them are suffering the consequences with the social and legal risks caused by the exposure of their data records. In fact, the concern towards offering secure ways of protecting data has escalated so rapidly over the last years that it took a great part of many of the discussions held at the World Economic Forum in January 2019. Motivated by this dire need for protecting data records, the first part of this project investigates successful ways of limiting the disclosure of private information held in a database when statistical information from it is released to the public. Examples of statistical information that is sold to third parties or released to the public include means, variances, or higher moments, as well as proportions of the population that satisfy certain conditions. However, we instead assume that we want to share the whole probability distribution, in the form of a density, without compromising the users' privacy. This leads us to the problem of density estimation, which is the second pillar of this project. Indeed, this project aims to combine these two lines of research to obtain a differentially private density estimator that is easily implemented using a neural network.

Abstract [sv]

En av de mest lovande möjligheterna för forskare under de senaste åren är förbättrad insamling av data och datans tillgänglighet. Dessutom har den stora mängden tvärvetenskapliga fält skapat möjligheter för datasamarbete. Under några år undersökte dock organisationer, företag och institutioner inte säkra sätt att hantera, bearbeta och dela data. Idag känner vi av konsekvenserna med de sociala och juridiska risker som orsakas av exponerade dataregister. Arbetet mot att erbjuda säkra sätt att försvara data har eskalerat så drastiskt över de senaste åren att det var en stor del av de diskussioner som hölls vid the World Economic Forum i Januari 2019. Drivet av det trängande behovet att försvara dataregister, undersöker första delen av det här projektet sätt att begränsa avslöjande av privat information i en databas när statistisk information från datan släpps till offentligheten. Exempel på statistisk information som säljs till tredjeparter eller släpps till allmänheten är medelvärden, varianser, högre moment, och andelar av populationen som uppfyller bestämda villkor. I vårt fall antar vi istället att vi vill dela hela sannolikhetsfördelningen, som en täthetsfunktion, utan att kompromissa med användarnas privatliv. Detta leder oss till density estimation, vilket är den andra grundpelaren i det här projektet. I själva verket syftar det här projektet att kombinera dessa två forskningsgrenar för att generera en differentierbar privat density estimator som enkelt kan implementeras med ett neuralt nätverk.

Place, publisher, year, edition, pages
2019. , p. 58
Series
TRITA-EECS-EX ; 2019:709
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:kth:diva-265666OAI: oai:DiVA.org:kth-265666DiVA, id: diva2:1380754
Educational program
Master of Science - Information and Network Engineering
Supervisors
Examiners
Available from: 2019-12-19 Created: 2019-12-19 Last updated: 2020-02-04Bibliographically approved

Open Access in DiVA

fulltext(2198 kB)12 downloads
File information
File name FULLTEXT02.pdfFile size 2198 kBChecksum SHA-512
54acfb07653d0e705d0c8b67d0bfcc3de9515107e41450bededcd8066a34f07917b9a61d80bfd3b65ceacb950b9860e2565bef1f4040dde3fa118899bd1f2e5a
Type fulltextMimetype application/pdf

By organisation
School of Electrical Engineering and Computer Science (EECS)
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 12 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 85 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf