Search Results for author:
Found 2 papers, 2 papers with code
LP-BFGS attack: An adversarial attack based on the Hessian with limited pixels
We study the attack performance and computation cost of the attack method based on the Hessian with a limited number of perturbation pixels.
Exploring Adversarial Examples and Adversarial Robustness of Convolutional Neural Networks by Mutual Information
Adversarial training is a simple and effective defense method to improve the robustness of CNNs to adversarial examples.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
