Secure and Flexible Information Sharing in Federated Systems

dc.contributor.advisorChen, Zhiyuan
dc.contributor.authorOni, Samson
dc.contributor.departmentInformation Systems
dc.contributor.programInformation Systems
dc.date.accessioned2022-02-09T15:52:47Z
dc.date.available2022-02-09T15:52:47Z
dc.date.issued2020-01-01
dc.description.abstractAs data grows exponentially, the need for information sharing to make meaningful decisions is on the increase. Multiple organizations leading different roles in dynamic situations often need to share mission-dependent data securely. Examples include contact tracing for a contagious disease such as COVID-19, maritime search and rescue operations, or creating a collaborative bid for a contract. In such examples, the ability to access data may need to change dynamically, depending on the situation of a mission (e.g., whether a person tested positive for a disease, a ship is in distress, or a bid-offer with given properties needs to be created). Also, there is a need to know how reliable data from each source is and improve the trust of multiple information by automatically detecting discrepancies among data from multiple sources. The current work does not address such a dynamic environment. In addition, most current work concerns data cleaning tools that use rules to detect data quality issues and most of these tools can only detect non-semantic issues. I have made two major contributions in this dissertations. The first is a framework to enable situation-aware access control in a federated Data-as-a-Service architecture by using Semantic Web technologies. This framework allows distributed query rewriting and semantic reasoning that automatically adds situation-based constraints to ensure that users can only see results they can access. We validate the framework by applying it to two dynamic use cases: maritime search and rescue operations and contact tracing for surveillance of a contagious disease. The experimental results of two use cases of SAR mission and Covid-19 demonstrate the effectiveness of the proposed framework. Organizations that need to share sensitive data sets securely during dynamic, limited duration scenarios can quickly adopt the framework. A second contribution is a novel approach for semantic discrepancy detection on data from multiple sources when some of the sources have structured data and other sources contain unstructured data. The proposed approach has three novel aspects: 1) a transfer learning method to extract information as entities from unstructured data automatically;2) algorithms to automatically match extracted entities with column data of other data sources; 3) algorithms to automatically detect semantic disparity between matched entities and column data across data sources. The experimental results on two events data sets and a disaster relief data set demonstrate the effectiveness and efficiency of the proposed methods. Multiple organizations collaborating to share data can quickly use the proposed methods.
dc.formatapplication:pdf
dc.genredissertations
dc.identifierdoi:10.13016/m2pmjv-kbql
dc.identifier.other12392
dc.identifier.urihttp://hdl.handle.net/11603/24199
dc.languageen
dc.relation.isAvailableAtThe University of Maryland, Baltimore County (UMBC)
dc.relation.ispartofUMBC Information Systems Department Collection
dc.relation.ispartofUMBC Theses and Dissertations Collection
dc.relation.ispartofUMBC Graduate School Collection
dc.relation.ispartofUMBC Student Collection
dc.sourceOriginal File Name: Oni_umbc_0434D_12392.pdf
dc.subjectdata disparity
dc.subjectdata quality
dc.subjectdeep learning
dc.subjectfederated systems
dc.subjectinformation extraction
dc.subjectmachine learning
dc.titleSecure and Flexible Information Sharing in Federated Systems
dc.typeText
dcterms.accessRightsAccess limited to the UMBC community. Item may possibly be obtained via Interlibrary Loan through a local library, pending author/copyright holder's permission.
dcterms.accessRightsThis item may be protected under Title 17 of the U.S. Copyright Law. It is made available by UMBC for non-commercial research and education. For permission to publish or reproduce, please see http://aok.lib.umbc.edu/specoll/repro.php or contact Special Collections at speccoll(at)umbc.edu

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Oni_umbc_0434D_12392.pdf
Size:
4.37 MB
Format:
Adobe Portable Document Format