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.
Nightmare at test time: robust learning by feature deletion
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2017 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
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.