Quantifying Information Leakage via Adversarial Loss Functions: Theory and Practice

Quantifying Information Leakage via Adversarial Loss Functions: Theory and Practice

abstract: Modern digital applications have significantly increased the leakage of private and sensitive personal data. While worst-case measures of leakage such as Differential Privacy (DP) provide the strongest guarantees, when utility matters, average-case information-theoretic measures can be mor...

Full description

Bibliographic Details
Other Authors: Liao, Jiachun (Author)
Format: Doctoral Thesis
Language:English
Published: 2020
Subjects:
Electrical engineering
Differential Privacy
Fairness
Generative adversarial models
Information leakage measure
Loss function
Privacy/Censoring
Online Access:http://hdl.handle.net/2286/R.I.57087

Internet

http://hdl.handle.net/2286/R.I.57087

Similar Items