Query-only access to kernel regression, SVM and KDE models suffices to reconstruct their exact training points, via a measure-theoretic proof and image experiments.
A kernel perspective of skip connections in convolutional networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Querying Kernel Methods Suffices for Reconstructing their Training Data
Query-only access to kernel regression, SVM and KDE models suffices to reconstruct their exact training points, via a measure-theoretic proof and image experiments.