163 papers with code • 9 benchmarks • 5 datasets
Competitions with currently unpublished results:
Its principled nature also enables us to identify methods for both training and attacking neural networks that are reliable and, in a certain sense, universal.
Then we propose a new dataset called ImageNet-P which enables researchers to benchmark a classifier's robustness to common perturbations.
In this work, we formalize the space of adversaries against deep neural networks (DNNs) and introduce a novel class of algorithms to craft adversarial samples based on a precise understanding of the mapping between inputs and outputs of DNNs.
We show how to turn any classifier that classifies well under Gaussian noise into a new classifier that is certifiably robust to adversarial perturbations under the $\ell_2$ norm.
We identify a trade-off between robustness and accuracy that serves as a guiding principle in the design of defenses against adversarial examples.
ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
However, different from leveraging attack transferability from substitute models, we propose zeroth order optimization (ZOO) based attacks to directly estimate the gradients of the targeted DNN for generating adversarial examples.
This paper presents deep compositional grammatical architectures which harness the best of two worlds: grammar models and DNNs.