How to build privacy and security into deep learning models
"Yishay Carmiel (IntelligentWire) shares techniques and explains how data privacy will impact machine learning development and how future training and inference will be affected. Yishay first dives into why training on private data should be addressed, federated learning, and differential priva...
| Autor Corporativo: | |
|---|---|
| Otros Autores: | |
| Formato: | Vídeo online |
| Idioma: | Inglés |
| Publicado: |
[Place of publication not identified] :
O'Reilly Media
2019.
|
| Materias: | |
| Ver en Biblioteca Universitat Ramon Llull: | https://discovery.url.edu/permalink/34CSUC_URL/1im36ta/alma991009822790306719 |
| Sumario: | "Yishay Carmiel (IntelligentWire) shares techniques and explains how data privacy will impact machine learning development and how future training and inference will be affected. Yishay first dives into why training on private data should be addressed, federated learning, and differential privacy. He then discusses why inference on private data should be addressed, homomorphic encryption and neural networks, a polynomial approximation of neural networks, protecting data in neural networks, data reconstruction from neural networks, and methods and techniques to secure data reconstruction from neural networks. This session was recorded at the 2019 O'Reilly Artificial Intelligence Conference in New York."--Resource description page. |
|---|---|
| Notas: | Title from title screen (viewed January 10, 2020). |
| Descripción Física: | 1 online resource (1 streaming video file (37 min., 44 sec.)) : digital, sound, color |
