Cyberspace has dramatically improved our daily lives in the past several decades. Meanwhile, people’s personal identifiable information (PII) is exposed online and is at risk of identity theft and cybercrimes. The Identity Ecosystem developed by the Center for Identity in the University of Texas at Austin addresses this problem and provides a statistical framework for understanding the value, risk and mutual relationships of PII. The Identity Ecosystem currently uses a general Bayesian Network Model to simulate the relationships among PII, which may be quite inaccurate for specific groups of people. This thesis proposes a solution that specializes the Bayesian Network used for particular groups of people. Both one-dimension specialization and multi-dimension specialization are investigated. Research problems like how to choose specialization criterion, how to set specialization boundaries, and how to overcome the difficult of insufficient data, are carefully studied. Specialization functionality is demonstrated based on empirical data. Finally, experiments of specialization are conducted on data obtained from online stories. This work is important in the sense that it provides a guide-line of designing more accurate models of PII within the Identity Ecosystem. / text
| Identifer | oai:union.ndltd.org:UTEXAS/oai:repositories.lib.utexas.edu:2152/29085 |
| Date | 09 March 2015 |
| Creators | Zhu, Liang, active 21st century |
| Source Sets | University of Texas |
| Language | English |
| Detected Language | English |
| Type | Thesis |
| Format | application/pdf |
Page generated in 0.002 seconds