Tipo di tesi
Tesi di laurea magistrale
Titolo
Privacy Risks of Local Explainers
Corso di studi
INFORMATICA
Parole chiave
- interpretable model
- local explainer
- membership inference attack
- privacy risk
Data inizio appello
02/12/2022
Consultabilità
Non consultabile
Data di rilascio
02/12/2092
Riassunto (Italiano)
The purpose of this thesis is to investigate how the privacy risk of a machine learning model seen as a black box changes when a more interpretable model is used to explain and locally approximate the behavior of the black box during the implementation of a Membership Inference Attack, an attack on a neural network that allows the attacker to determine if a particular datum was part of the training set used to train the black box.
