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.
Macer: Attack-free and scalable robust training via maximizing certified radius.arXiv preprint arXiv:2001.02378, 2020
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
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.