Catelli, Rosario (2021) Safeguarding Privacy Through Deep Learning Techniques. [Tesi di dottorato]
Anteprima |
Testo
catelli_rosario_33.pdf Download (1MB) | Anteprima |
| Tipologia del documento: | Tesi di dottorato |
|---|---|
| Lingua: | English |
| Titolo: | Safeguarding Privacy Through Deep Learning Techniques |
| Autori: | Autore Email Catelli, Rosario rosario.catelli@unina.it |
| Data: | 13 Aprile 2021 |
| Numero di pagine: | 125 |
| Istituzione: | Università degli Studi di Napoli Federico II |
| Dipartimento: | Ingegneria Elettrica e delle Tecnologie dell'Informazione |
| Dottorato: | Information technology and electrical engineering |
| Ciclo di dottorato: | 33 |
| Coordinatore del Corso di dottorato: | nome email Riccio, Daniele daniele.riccio@unina.it |
| Tutor: | nome email Casola, Valentina [non definito] Esposito, Massimo [non definito] |
| Data: | 13 Aprile 2021 |
| Numero di pagine: | 125 |
| Parole chiave: | privacy, deep learning, clinical de-identification |
| Settori scientifico-disciplinari del MIUR: | Area 09 - Ingegneria industriale e dell'informazione > ING-INF/05 - Sistemi di elaborazione delle informazioni |
| Informazioni aggiuntive: | Google Scholar Profile for updated contact email: https://scholar.google.it/citations?user=Ge-RyG4AAAAJ&hl=it&oi=ao - OrcID Profile: https://orcid.org/0000-0001-5598-6477 |
| Depositato il: | 10 Mag 2021 23:23 |
| Ultima modifica: | 07 Giu 2023 10:34 |
| URI: | http://www.fedoa.unina.it/id/eprint/13880 |
Abstract
Over the last few years, there has been a growing need to meet minimum security and privacy requirements. Both public and private companies have had to comply with increasingly stringent standards, such as the ISO 27000 family of standards, or the various laws governing the management of personal data. The huge amount of data to be managed has required a huge effort from the employees who, in the absence of automatic techniques, have had to work tirelessly to achieve the certification objectives. Unfortunately, due to the delicate information contained in the documentation relating to these problems, it is difficult if not impossible to obtain material for research and study purposes on which to experiment new ideas and techniques aimed at automating processes, perhaps exploiting what is in ferment in the scientific community and linked to the fields of ontologies and artificial intelligence for data management. In order to bypass this problem, it was decided to examine data related to the medical world, which, especially for important reasons related to the health of individuals, have gradually become more and more freely accessible over time, without affecting the generality of the proposed methods, which can be reapplied to the most diverse fields in which there is a need to manage privacy-sensitive information.
Downloads
Downloads per month over past year
Actions (login required)
 |
Modifica documento |
