Unifying Adversarial Training Algorithms with Data Gradient Regularization

26 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

A Closer Look at Accuracy vs. Robustness (2020, methodology): “Future progress that ensures both robustness and accuracy may come from redesigning other aspects of the training process, such as customized optimization methods [3, 15, 25, 34, 43, 50, 52, 51] or better network architectures [13, 47, 69] in combination with loss functions that encourage adversaria”
Gradient Adversarial Training of Neural Networks (2018, background): “…Previous attempts at adversarial defenses have focused on minimizing (cid:107)∇ J ( θ, x + ∆ , y ) p locally at the training points [22, 25, 13, 9]. curvature (cid:107) However, this leads to a sharp of the loss surface near those points, violating the ﬁrst order Taylor approximation,…”