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
3 Pith papers cite this work. Polarity classification is still indexing.
3
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.
citing papers explorer
-
Certified Robustness under Heterogeneous Perturbations via Hybrid Randomized Smoothing
A hybrid randomized smoothing method yields a closed-form certificate for joint discrete-continuous perturbations that generalizes prior Gaussian and discrete smoothing approaches.
-
Fortifying Time Series: DTW-Certified Robust Anomaly Detection
First DTW-certified robust anomaly detection for time series via randomized smoothing adapted through an l_p-to-DTW lower-bound transformation.
-
Towards Deep Learning Models Resistant to Adversarial Attacks
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.