Backdoors can be embedded in ResNet and ViT models as statistically indistinguishable latent directions, reducing cryptographic undetectability to an intractable hypothesis test over parameter distributions.
Title resolution pending
2 Pith papers cite this work, alongside 383 external citations. Polarity classification is still indexing.
2
Pith papers citing it
383
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative 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
-
Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks
Backdoors can be embedded in ResNet and ViT models as statistically indistinguishable latent directions, reducing cryptographic undetectability to an intractable hypothesis test over parameter distributions.
-
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%.