一句话:提出对深度神经网络模型进行白盒静态分析,识别易误分类的脆弱类别并重训练以提升鲁棒性。
本文关注深度神经网络模型在分类任务中的鲁棒性问题,特别是那些容易被误分类的脆弱类别。其方法采用白盒方式静态分析模型的内部结构,从中提取可用于识别脆弱类别的信息。在定位到这些易受影响的类别后,作者提出针对性地重训练这些类别,以提升模型的鲁棒性。初步评估在 MNIST、F-MNIST 以及 CIFAR-10(使用 ImageNet 和 ResNet-32 模型)等数据集上开展,并与两个 state-of-the-art 检测器进行对比,结果初步验证了该方法的有效性。
This work studies the static structure of deep neural network models using white box based approach and utilizes that knowledge to find the susceptible classes which can be misclassified easily. With the knowledge of susceptible classes, our work has proposed to retrain the model for those classes to achieve increased robustness. Our preliminary result has been evaluated on MNIST, F-MNIST, and CIFAR-10 (ImageNet and ResNet-32 model) based datasets and have been compared with two state-of-the-art detectors.
DOI 原文 ·
@inproceedings{paperbot5161,
title = {Static deep neural network analysis for robustness},
author = {Rangeet Pan},
booktitle = {FSE},
year = {2019},
doi = {10.1145/3338906.3342502}
}