1 code implementation • 1 May 2020 • Hojjat Aghakhani, Dongyu Meng, Yu-Xiang Wang, Christopher Kruegel, Giovanni Vigna
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.
4 code implementations • 25 May 2017 • Dongyu Meng, Hao Chen
Different from previous work, MagNet learns to differentiate between normal and adversarial examples by approximating the manifold of normal examples.