Sung-Min Hong

collaborators

2 papers

cs.CV2020

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 $ε$ on the adversarial example $X_{a d v}$ ( $=$ $X$ $\pm$ $ε$ , $X$ is a benign sample) by subtracting the estimated…

cs.LG2018

Controlling the privacy loss with the input feature maps of the layers in convolutional neural networks

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

We propose the method to sanitize the privacy of the IFM(Input Feature Map)s that are fed into the layers of CNN(Convolutional Neural Network)s. The method introduces the degree of…