A hybrid randomized smoothing method yields a closed-form certificate for joint discrete-continuous perturbations that generalizes prior Gaussian and discrete smoothing approaches.
Second-order ad- versarial attack and certifiable robustness.arXiv preprint arXiv:1809.03113
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2representative citing papers
First DTW-certified robust anomaly detection for time series via randomized smoothing adapted through an l_p-to-DTW lower-bound transformation.
Adversarial training via projected gradient descent on the inner maximization problem produces neural networks with substantially improved resistance to a wide range of attacks and establishes security against first-order adversaries as a concrete guarantee.
A preprocessor of Gaussian noise plus bilateral filtering yields supralinear adversarial robustness in CNNs and, when paired with adversarial training, ranks near the top of RobustBench while using far less compute, parameters, epochs, and data than prior defenses.
citing papers explorer
No citing papers match the current filters.