Fighting Uphill Battles: Improvements in Personal Data Privacy
dc.contributor.author
Sommer, David Marco
dc.contributor.supervisor
Capkun, Srdjan
dc.contributor.supervisor
Mittal, Prateek
dc.contributor.supervisor
Mohammadi, Esfandiar
dc.contributor.supervisor
Papernot, Nicolas
dc.contributor.supervisor
Vechev, Martin
dc.date.accessioned
2021-10-11T06:26:50Z
dc.date.available
2021-10-09T13:19:39Z
dc.date.available
2021-10-11T06:26:50Z
dc.date.issued
2021
dc.identifier.uri
http://hdl.handle.net/20.500.11850/508911
dc.identifier.doi
10.3929/ethz-b-000508911
dc.description.abstract
With the rise of modern information technology and the Internet, the worldwide interconnectivity is resulting in a massive collection and evaluation of potentially sensitive data, often out of control of those affected. The increasing impact of this data stream and the potential for its abuse raise concern, calling for protection against emerging exploitations and fear-driven self-censorship. The ability of individuals or a group to limit this flow and to express themselves selectively is commonly subsumed under the umbrella term \textit{privacy}. This thesis tackles the digital generation, processing, and control of personal information, so-called individual data privacy, from multiple angles. First, it introduces the concept of passive participation, enabling users to access information over the Internet while hiding in cover traffic passively generated by regular users of frequently visited websites. This solves the bootstrapping problem for mid- and high-latency anonymous communication networks where an adversary might collect thousands of traffic observations. Next, we analyze the statistical privacy leakage of multiple such sequential adversarial observations in the information-theoretic framework of differential privacy that aims to limit and blur the impact of individuals. There, we propose the privacy loss distribution, unifying several other often used differential privacy notions, and show that it converges towards a Gaussian shape under independent sequential composition of observations, allowing the classification of differentially private mechanisms into privacy loss classes defined by the parameters of said Gaussian distribution. However, more blurring means less accurate results, the inherent privacy-utility trade-off. We applied a gradient descent optimizer and learned utility-loss-minimizing truncated noise patterns for differentially private mechanisms that blur the impact of individuals by adding the learned noise to sensitivity-bounded outputs. Our results suggest that Gaussian additive noise is close to optimal, especially under sequential composition. Finally, we tackle the trust problem in truthfully executed deletion requests for personal data and provide a framework for probabilistic verification of such requests while demonstrating its feasibility for the case of machine learning.
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.publisher
ETH Zurich
en_US
dc.rights.uri
http://rightsstatements.org/page/InC-NC/1.0/
dc.subject
Differential privacy
en_US
dc.subject
Machine learning
en_US
dc.subject
Anonymous communication
en_US
dc.title
Fighting Uphill Battles: Improvements in Personal Data Privacy
en_US
dc.type
Doctoral Thesis
dc.rights.license
In Copyright - Non-Commercial Use Permitted
dc.date.published
2021-10-11
ethz.size
262 p.
en_US
ethz.code.ddc
DDC - DDC::5 - Science::500 - Natural sciences
en_US
ethz.identifier.diss
27893
en_US
ethz.publication.place
Zurich
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02150 - Dep. Informatik / Dep. of Computer Science::02660 - Institut für Informationssicherheit / Institute of Information Security::03755 - Capkun, Srdan / Capkun, Srdan
en_US
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02150 - Dep. Informatik / Dep. of Computer Science::02660 - Institut für Informationssicherheit / Institute of Information Security::03755 - Capkun, Srdan / Capkun, Srdan
en_US
ethz.date.deposited
2021-10-09T13:19:49Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2021-10-11T06:26:58Z
ethz.rosetta.lastUpdated
2022-03-29T14:07:37Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Fighting%20Uphill%20Battles:%20Improvements%20in%20Personal%20Data%20Privacy&rft.date=2021&rft.au=Sommer,%20David%20Marco&rft.genre=unknown&rft.btitle=Fighting%20Uphill%20Battles:%20Improvements%20in%20Personal%20Data%20Privacy
Files in this item
Publication type
-
Doctoral Thesis [30551]