Exact composition of mechanisms under multiple simultaneous DP constraints is represented as a mixture of heterogeneous compositions using a structural lemma for binary hypothesis tests.
Computing differential privacy guarantees for heterogeneous compositions using fft, 2021
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
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.
citing papers explorer
-
Composition Theorems for Multiple Differential Privacy Constraints
Exact composition of mechanisms under multiple simultaneous DP constraints is represented as a mixture of heterogeneous compositions using a structural lemma for binary hypothesis tests.
-
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.