Analysis of Data Security Vulnerabilities in Deep Learning
| dc.contributor.advisor | Czaja, Wojciech | en_US |
| dc.contributor.advisor | Goldstein, Thomas | en_US |
| dc.contributor.author | Fowl, Liam | en_US |
| dc.contributor.department | Mathematics | en_US |
| dc.contributor.publisher | Digital Repository at the University of Maryland | en_US |
| dc.contributor.publisher | University of Maryland (College Park, Md.) | en_US |
| dc.date.accessioned | 2022-06-21T05:35:36Z | |
| dc.date.available | 2022-06-21T05:35:36Z | |
| dc.date.issued | 2022 | en_US |
| dc.description.abstract | As deep learning systems become more integrated into important application areas, the security of such systems becomes a paramount concern. Specifically, as modern networks require an increasing amount of data on which to train, the security of data that is collected for these models cannot be guaranteed. In this work, we investigate several security vulnerabilities and security applications of the data pipeline for deep learning systems. We systematically evaluate the risks and mechanisms of data security from multiple perspectives, ranging from users to large companies and third parties, and reveal several security mechanisms and vulnerabilities that are of interest to machine learning practitioners. | en_US |
| dc.identifier | https://doi.org/10.13016/yvog-ixni | |
| dc.identifier.uri | http://hdl.handle.net/1903/28927 | |
| dc.language.iso | en | en_US |
| dc.subject.pqcontrolled | Mathematics | en_US |
| dc.subject.pqcontrolled | Computer science | en_US |
| dc.subject.pquncontrolled | Data Poisoning | en_US |
| dc.subject.pquncontrolled | Deep Learning | en_US |
| dc.subject.pquncontrolled | Federated Learning | en_US |
| dc.subject.pquncontrolled | Machine Learning | en_US |
| dc.subject.pquncontrolled | Privacy | en_US |
| dc.subject.pquncontrolled | Robustness | en_US |
| dc.title | Analysis of Data Security Vulnerabilities in Deep Learning | en_US |
| dc.type | Dissertation | en_US |
Files
Original bundle
1 - 1 of 1