Reinforcing the Robustness of a Deep Neural Network to Adversarial Examples by Using Color Quantization of Training Image Data
Lists
Only you see this
Abstract
Recent works have shown the vulnerability of deep convolutional neural network (DCNN) to adversarial examples with malicious perturbations. In particular, Black-Box attacks without information of parameter and architectures of the target models are feared as realistic threats. To address this problem, we propose a method using an ensemble of models trained by color-quantized data with loss maximization. Color-quantization can allow the trained models to focus on learning conspicuous spatial features to enhance the robustness of DCNNs to adversarial examples. The proposed method can be adapted to Black-Box attacks with no need of particular attack algorithm for the defense. The results of our experiments validated the effectiveness for preventing decrease in the test accuracy with adversarial perturbation.
BibTeX
@inproceedings{miyazato2019reinforcing,
author = {Shuntaro Miyazato and Xueting Wang and Toshihiko Yamasaki and Kiyoharu Aizawa},
title = {{Reinforcing the Robustness of a Deep Neural Network to Adversarial Examples by Using Color Quantization of Training Image Data}},
booktitle = {ICIP},
year = {2019},
doi = {10.1109/icip.2019.8802996},
}Loading related content...