一句话：提出面向数据的变异框架 Styx，通过轻微变异训练数据提升 DNN 鲁棒性并保持测试精度。
深度神经网络（DNN）的鲁棒性难以保证。本文提出一种通用的、面向数据的变异框架 Styx，通过轻微变异训练数据生成新的训练样本，从而在保持测试集精度的同时提升模型对小扰动的适应能力，即鲁棒性。作者针对图像分类实例化了 Styx，并提出适用于任意图像分类 DNN 的像素级变异规则。在多个常用基准上，将 Styx 与代表性对抗训练方法进行比较，初步实验结果表明 Styx 有效。
The robustness of deep neural network (DNN) is critical and challenging to ensure. In this paper, we propose a general data-oriented mutation framework, called Styx, to improve the robustness of DNN. Styx generates new training data by slightly mutating the training data. In this way, Styx ensures the DNN's accuracy on the test dataset while improving the adaptability to small perturbations, i.e., improving the robustness. We have instantiated Styx for image classification and proposed pixel-level mutation rules that are applicable to any image classification DNNs. We have applied Styx on several commonly used benchmarks and compared Styx with the representative adversarial training methods. The preliminary experimental results indicate the effectiveness of Styx.
DOI 原文 ·
@inproceedings{paperbot5972,
title = {Styx},
author = {Meixi Liu and Weijiang Hong and Weiyu Pan and Chendong Feng and Zhenbang Chen and Ji Wang},
booktitle = {ASE},
year = {2020},
doi = {10.1145/3324884.3418903}
}