Rotationally equivariant quantum models can rely on vulnerable invariant statistics such as ring-averaged intensities, leaving them susceptible to classical transfer attacks, but suppressing the associated symmetry sectors substantially improves robustness.
Adversarial Examples Are Not Bugs, They Are Features
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
Introduces IFM loss regularization for CNNs to learn correlated discriminative features, tested on shiftedMNIST dataset.
Thesis uses statistical mechanics to study DAM and RBM models for understanding memorization, low-dimensional learning, and adversarial robustness in neural networks.
SleepNet and DreamNet enrich visual features via supervised pre-trained encoders and reconstruct hidden states with encoder-decoder frameworks to outperform prior state-of-the-art classifiers.
citing papers explorer
-
SleepNet and DreamNet: Enriching and Reconstructing Representations for Consolidated Visual Classification
SleepNet and DreamNet enrich visual features via supervised pre-trained encoders and reconstruct hidden states with encoder-decoder frameworks to outperform prior state-of-the-art classifiers.