Differential halo zonotopes enable static verification of global robustness in DNNs by jointly propagating pairs of perturbed inputs while bounding divergence, with a relaxed confidence-based variant.
Revisiting differential verification: Equivalence verification with confidence
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CR 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Introduces formal verification to compute certified neuron range bounds for CKKS-encrypted neural networks, eliminating overflow failures that previously reached 47%.
citing papers explorer
-
Differential Zonotopes for Verifying Global Robustness of DNNs
Differential halo zonotopes enable static verification of global robustness in DNNs by jointly propagating pairs of perturbed inputs while bounding divergence, with a relaxed confidence-based variant.
-
Encrypted Neural Networks without Overflows
Introduces formal verification to compute certified neuron range bounds for CKKS-encrypted neural networks, eliminating overflow failures that previously reached 47%.