SWAN: A Framework to Bootstrap Trust in Network Data Science

dc.contributor.advisor	Durairajan, Ramakrishnan
dc.contributor.author	Elfandi, Abduarraheem
dc.date.accessioned	2024-08-07T19:56:46Z
dc.date.available	2024-08-07T19:56:46Z
dc.date.issued	2024-08-07
dc.description.abstract	Two significant challenges must be overcome before machine learning models can be deployed in an operational setting: the ability to achieve trust within and across enclaves which includes addressing data privacy concerns. In this thesis, we propose SWAN, a framework to tackle these challenges by allowing data to be labeled at scale, achieving trust within an enclave by providing insight into black-box machine learning models through a hybrid explainability technique which is done by utilizing the combination of global and local interpretability techniques. Furthermore, the framework allows for collaboration across enclaves while maintaining data privacy requirements. This thesis includes unpublished co-authored material by Ramakrishnan Durairajan and Walter Willinger.	en_US
dc.identifier.uri	https://hdl.handle.net/1794/29700
dc.language.iso	en_US
dc.publisher	University of Oregon
dc.rights	All Rights Reserved.
dc.title	SWAN: A Framework to Bootstrap Trust in Network Data Science
dc.type	Electronic Thesis or Dissertation
thesis.degree.discipline	Department of Computer Science
thesis.degree.grantor	University of Oregon
thesis.degree.level	masters
thesis.degree.name	M.S.

Files

Now showing 1 - 1 of 1