A new framework is introduced for end-to-end provable robustness against backdoor attacks by composing randomized smoothing with differentially private training via privacy profiles.
Numerical composition of differential privacy, 2021
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
The Edgeworth Accountant uses the Edgeworth expansion on privacy-loss log-likelihood ratios to derive closed-form non-asymptotic (ε, δ)-DP bounds for composed noise-addition mechanisms.
citing papers explorer
-
Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy
A new framework is introduced for end-to-end provable robustness against backdoor attacks by composing randomized smoothing with differentially private training via privacy profiles.
-
Edgeworth Accountant: An Analytical Approach to Differential Privacy Composition
The Edgeworth Accountant uses the Edgeworth expansion on privacy-loss log-likelihood ratios to derive closed-form non-asymptotic (ε, δ)-DP bounds for composed noise-addition mechanisms.