A regression-tree-based method computes guaranteed bounds on the safe output probability for neural networks under probabilistic inputs by generating safe and unsafe hulls via boundary-aware sampling and prioritized refinement.
CoRRabs/2206.12227(2022)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2roles
background 1polarities
background 1representative citing papers
NTGA is the first clean-label generalization attack under black-box settings but is vulnerable to adversarial training and image transformations, with newer attacks outperforming it.
citing papers explorer
-
Probabilistic Verification of Neural Networks via Efficient Probabilistic Hull Generation
A regression-tree-based method computes guaranteed bounds on the safe output probability for neural networks under probabilistic inputs by generating safe and unsafe hulls via boundary-aware sampling and prioritized refinement.
-
SoK: A Comprehensive Analysis of the Current Status of Neural Tangent Generalization Attacks with Research Directions
NTGA is the first clean-label generalization attack under black-box settings but is vulnerable to adversarial training and image transformations, with newer attacks outperforming it.