Defending Against Adversarial Attacks by Suppressing the Largest Eigenvalue of Fisher Information Matrix

no code implementations • 13 Sep 2019 • Chaomin Shen, Yaxin Peng, Guixu Zhang, Jinsong Fan

We propose a scheme for defending against adversarial attacks by suppressing the largest eigenvalue of the Fisher information matrix (FIM).

Adversarial Defense Traffic Sign Recognition