Adversarial Training

DropAttack is an adversarial training method that adds intentionally worst-case adversarial perturbations to both the input and hidden layers in different dimensions and minimizes the adversarial risks generated by each layer.

Source: DropAttack: A Masked Weight Adversarial Training Method to Improve Generalization of Neural Networks


Paper Code Results Date Stars


Task Papers Share
Adversarial Attack 1 50.00%
Adversarial Defense 1 50.00%


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign