Theoretical soundness of neural network verifiers does not guarantee soundness for deployed floating-point models; all tested verifiers are fooled by deployment-triggered backdoors.
Output range analysis for deep feedforward neural networks
1 Pith paper cite this work, alongside 7 external citations. Polarity classification is still indexing.
1
Pith paper citing it
7
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
No Soundness in the Real World: On the Challenges of the Verification of Deployed Neural Networks
Theoretical soundness of neural network verifiers does not guarantee soundness for deployed floating-point models; all tested verifiers are fooled by deployment-triggered backdoors.