Detecting Adversarial Examples in Deep Neural Networks using Normalizing Filters

Shuangchi Gu, Ping Yi, Ting Zhu, Yao Yao, Wei Wang

Abstract

Deep neural networks are vulnerable to adversarial examples which are inputs modified with unnoticeable but malicious perturbations. Most defending methods only focus on tuning the DNN itself, but we propose a novel defending method which modifies the input data to detect the adversarial examples. We establish a detection framework based on normalizing filters that can partially erase those perturbations by smoothing the input image or depth reduction work. The framework gives the decision by comparing the classification results of original input and multiple normalized inputs. Using several combinations of gaussian blur filter, median blur filter and depth reduction filter, the evaluation results reaches a high detection rate and achieves partial restoration work of adversarial examples in MNIST dataset. The whole detection framework is a low-cost highly extensible strategy in DNN defending works.

Download


Paper Citation


in Harvard Style

Gu S., Yi P., Zhu T., Yao Y. and Wang W. (2019). Detecting Adversarial Examples in Deep Neural Networks using Normalizing Filters.In Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-350-6, pages 164-173. DOI: 10.5220/0007370301640173


in Bibtex Style

@conference{icaart19,
author={Shuangchi Gu and Ping Yi and Ting Zhu and Yao Yao and Wei Wang},
title={Detecting Adversarial Examples in Deep Neural Networks using Normalizing Filters},
booktitle={Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2019},
pages={164-173},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007370301640173},
isbn={978-989-758-350-6},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Detecting Adversarial Examples in Deep Neural Networks using Normalizing Filters
SN - 978-989-758-350-6
AU - Gu S.
AU - Yi P.
AU - Zhu T.
AU - Yao Y.
AU - Wang W.
PY - 2019
SP - 164
EP - 173
DO - 10.5220/0007370301640173