Show simple item record

FieldValueLanguage
dc.contributor.authorNan, Lihao
dc.date.accessioned2019-07-01
dc.date.available2019-07-01
dc.date.issued2019-02-21
dc.identifier.urihttp://hdl.handle.net/2123/20662
dc.description.abstractHere we consider a common data encryption problem encountered by users who want to disclose some data to gain utility but preserve their private information. Specifically, we consider the inference attack, in which an adversary conducts inference on the disclosed data to gain information about users' private data. Following privacy funnel \cite{makhdoumi2014information}, assuming that the original data $X$ is transformed into $Z$ before disclosing and the log loss is used for both privacy and utility metrics, then the problem can be modeled as finding a mapping $X \rightarrow Z$ that maximizes mutual information between $X$ and $Z$ subject to a constraint that the mutual information between $Z$ and private data $S$ is smaller than a predefined threshold $\epsilon$. In contrast to the original study \cite{makhdoumi2014information}, which only focused on discrete data, we consider the more general and practical setting of continuous and high-dimensional disclosed data (e.g., image data). Most previous work on privacy-preserving representation learning is based on adversarial learning or generative adversarial networks, which has been shown to suffer from the vanishing gradient problem, and it is experimentally difficult to eliminate the relationship with private data $Y$ when $Z$ is constrained to retain more information about $X$. Here we propose a simple but effective variational approach that does not rely on adversarial training. Our experimental results show that our approach is stable and outperforms previous methods in terms of both downstream task accuracy and mutual information estimation.en_AU
dc.rightsThe author retains copyright of this thesis. It may only be used for the purposes of research and study. It must not be used for any other purposes and may not be transmitted or shared with others without prior permission.en_AU
dc.subjectPrivacyen_AU
dc.subjectData securityen_AU
dc.subjectRepresentationen_AU
dc.subjectLearningen_AU
dc.titlePrivacy Preserving Representation Learning For Complex Dataen_AU
dc.typeThesisen_AU
dc.type.thesisMasters by Researchen_AU
usyd.facultyFaculty of Engineering and Information Technologies, School of Computer Scienceen_AU
usyd.degreeMaster of Engineering M.E.en_AU
usyd.awardinginstThe University of Sydneyen_AU


Show simple item record

Associated file/s

Associated collections

Show simple item record

There are no previous versions of the item available.