Presents Evolving Abstract Transformers with UPOSE and AGG algorithms to create adaptable, domain-agnostic sound transformers for polyhedral abstract domains in program analysis.
Input-relational verification of deep neural networks.Proc
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
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
-
Evolving Abstract Transformers for Gradient-Guided, Adaptable Abstract Interpretation
Presents Evolving Abstract Transformers with UPOSE and AGG algorithms to create adaptable, domain-agnostic sound transformers for polyhedral abstract domains in program analysis.