Search Results for author:
Found 2 papers, 2 papers with code
Bullseye Polytope: A Scalable Clean-Label Poisoning Attack with Improved Transferability
Our attack, Bullseye Polytope, improves the attack success rate of the current state-of-the-art by 26. 75% in end-to-end transfer learning, while increasing attack speed by a factor of 12.
MagNet: a Two-Pronged Defense against Adversarial Examples
Different from previous work, MagNet learns to differentiate between normal and adversarial examples by approximating the manifold of normal examples.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
