DAPAS : Denoising Autoencoder to Prevent Adversarial attack in Semantic Segmentation
Abstract
Nowadays, Deep learning techniques show dramatic performance on computer vision area, and they even outperform human. But it is also vulnerable to some small perturbation called an adversarial attack. This is a problem combined with the safety of artificial intelligence, which has recently been studied a lot. These attacks have shown that they can fool models of image classification, semantic segmentation, and object detection. We point out this attack can be protected by denoise autoencoder, which is used for denoising the perturbation and restoring the original images. We experiment with various noise distributions and verify the effect of denoise autoencoder against adversarial attack in semantic segmentation.
Cite
@article{arxiv.1908.05195,
title = {DAPAS : Denoising Autoencoder to Prevent Adversarial attack in Semantic Segmentation},
author = {Seungju Cho and Tae Joon Jun and Byungsoo Oh and Daeyoung Kim},
journal= {arXiv preprint arXiv:1908.05195},
year = {2020}
}
Comments
Accepted to be published in: 2020 International Joint Conference on Neural Networks (IJCNN), Glasgow, July 19--24, 2020