Mitigating large adversarial perturbations on X-MAS (X minus Moving Averaged Samples)

Woohyung Chun, Sung-Min Hong, Junho Huh +1

We propose the scheme that mitigates the adversarial perturbation $\epsilon$ on the adversarial example $X_{adv}$ ($=$ $X$ $\pm$ $\epsilon$, $X$ is a benign sample) by subtracting the estimated…