Introduces formal verification to compute certified neuron range bounds for CKKS-encrypted neural networks, eliminating overflow failures that previously reached 47%.
Minimax approximation of sign function by composite polynomial for homomorphic comparison.IEEE Transactions on Dependable and Secure Computing, 19(6):3711–3727
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A benchmarking experiment finds low rediscovery rates for three models on six Mythos-linked bug tasks, with only six target matches across 54 attempts under controlled prompting.
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%.
-
Benchmarking Mythos-Linked Bug Rediscovery
A benchmarking experiment finds low rediscovery rates for three models on six Mythos-linked bug tasks, with only six target matches across 54 attempts under controlled prompting.