Backdoors can be realized as statistically natural latent directions in modern neural networks, achieving high attack success with negligible clean accuracy loss and resisting existing defenses.
Random features for large-scale kernel machines.Advances in neural information processing systems, 20
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 3
method 1
citation-polarity summary
verdicts
UNVERDICTED 6representative citing papers
Directional Chebyshev harmonics enable spectral path regression for tabular data with closed-form training, competitive accuracy, and explicit interpretability.
Sparse RFNNs with sSVD via Lanczos-Golub-Kahan bidiagonalization maintain accuracy while improving efficiency and robustness for 1D steady convection-diffusion equations with strong advection.
The Neural Basis Method uses a predefined neural basis space and operator residual metric to deliver accurate single solves and fast parametric learning for multiscale Darcian dynamics.
Negative-capable ridge regression uses controlled negative regularization as anti-shrinkage to increase effective complexity along weak eigendirections and mitigate underfitting in small-data regression.
A review synthesizing foundations, constructions, advantage conditions, and challenges for non-variational quantum kernel methods in supervised learning.
citing papers explorer
-
Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks
Backdoors can be realized as statistically natural latent directions in modern neural networks, achieving high attack success with negligible clean accuracy loss and resisting existing defenses.
-
Spectral Path Regression: Directional Chebyshev Harmonics for Interpretable Tabular Learning
Directional Chebyshev harmonics enable spectral path regression for tabular data with closed-form training, competitive accuracy, and explicit interpretability.
-
Sparse Random-Feature Neural Networks with Krylov-Based SVD for Singularly Perturbed ODE
Sparse RFNNs with sSVD via Lanczos-Golub-Kahan bidiagonalization maintain accuracy while improving efficiency and robustness for 1D steady convection-diffusion equations with strong advection.
-
Solving and learning advective multiscale Darcian dynamics with the Neural Basis Method
The Neural Basis Method uses a predefined neural basis space and operator residual metric to deliver accurate single solves and fast parametric learning for multiscale Darcian dynamics.
-
A Ridge Too Far: Correcting Over-Shrinkage via Negative Regularization
Negative-capable ridge regression uses controlled negative regularization as anti-shrinkage to increase effective complexity along weak eigendirections and mitigate underfitting in small-data regression.
-
Non-variational supervised quantum kernel methods: a review
A review synthesizing foundations, constructions, advantage conditions, and challenges for non-variational quantum kernel methods in supervised learning.