Introduces formal verification to compute certified neuron range bounds for CKKS-encrypted neural networks, eliminating overflow failures that previously reached 47%.
Privacy-preserving neural networks with homomorphic encryption: C hallenges and opportunities.Peer-to-Peer Networking and Applications, 14(3):1666–1691
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
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%.