Formulates quadratic ReLU replacement as a linear separation problem in lifted space, with exact conditions for calibration-lossless replacement and convex relaxations for approximate cases, achieving plaintext accuracy at lower cost under CKKS.
Precise approximation of convolutional neural networks for homomorphically encrypted data,
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
-
Decision-Aware Quadratic ReLU Replacement for HE-Friendly Inference
Formulates quadratic ReLU replacement as a linear separation problem in lifted space, with exact conditions for calibration-lossless replacement and convex relaxations for approximate cases, achieving plaintext accuracy at lower cost under CKKS.
-
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%.