SecureCROWN enables privacy-preserving neural network robustness verification via secure two-party computation, eliminating data-dependent branching using ReLU arithmetic and Newton-Raphson refinement.
Function se- cret sharing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Privacy-Preserving Robustness Verification for Neural Networks
SecureCROWN enables privacy-preserving neural network robustness verification via secure two-party computation, eliminating data-dependent branching using ReLU arithmetic and Newton-Raphson refinement.