This paper explores the synergy between machine learning and differential privacy to safeguard sensitive data in the information age. It addresses the significance of machine learning in data-driven decision-making and introduces differential privacy as a key technique to ensure data privacy. Practical applications are examined, and Federated Learning is mentioned as a distributed approach.
Questo elaborato esplora il connubio tra machine learning e differential privacy per proteggere i dati sensibili nell'era dell'informazione. Affronta l'importanza del machine learning nelle decisioni basate sui dati e presenta la differential privacy come una tecnica chiave per garantire la privacy dei dati. Vengono esaminate applicazioni pratiche e menzionato il Federated Learning come approccio distribuito.
MODELLI DI MACHINE LEARNING PRIVATI CON DIFFERENTIAL PRIVACY
PONTRANDOLFO, MARCO
2022/2023
Abstract
This paper explores the synergy between machine learning and differential privacy to safeguard sensitive data in the information age. It addresses the significance of machine learning in data-driven decision-making and introduces differential privacy as a key technique to ensure data privacy. Practical applications are examined, and Federated Learning is mentioned as a distributed approach.| File | Dimensione | Formato | |
|---|---|---|---|
|
TESI GIUSTA Con Liberatoria .pdf
File consultabile da postazioni biblioteca
Descrizione: tesi di laurea
Dimensione
3.35 MB
Formato
Adobe PDF
|
3.35 MB | Adobe PDF |
I documenti in UNITESI sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/20.500.14253/66406