一句话：提出基于引导符号执行的像素级CNN可解释方法，并用于提升对抗鲁棒性。
卷积神经网络（CNN）广泛用于图像分类，但训练后的模型是高复杂度非线性系统，其隐含决策知识难以被人类理解。现有可解释方法的解释精度不足，难以准确说明分类依据。本文提出一种基于引导符号执行策略的新型像素级可解释方法，用于解释CNN对输入图像的分类基础。作者在PyTorch团队发布的CNN模型上进行了大量实验，结果表明，与现有可解释方法相比，该方法在像素级解释分类依据方面具有100%的准确性。此外，本文基于所提出的可解释方法设计了一种增强CNN模型对抗鲁棒性的方案。评估实验表明，该方案能有效提升CNN模型的对抗鲁棒性，并且在具有不同结构的CNN模型之间具有可迁移性。
Convolutional neural network (CNN) currently has been widely used to undertake the task of image classification. Unfortunately, a trained CNN model is a nonlinear system with high complexity, and the implicit decision knowledge carried by the CNN model is often difficult to be comprehended by humans. A feasible method to make human understanding of decision knowledge is to explain the classification basis of the trained CNN model. In order to solve the problem of insufficient interpretation accuracy of the existing methods, this paper presents a novel pixel-level explainable approach based on a guided symbolic execution strategy. A large number of experiments are conducted on the PyTorch team published CNN models, and the experimental results show that the presented approach is a 100% accurate technique for interpreting classification basis of input images on pixel-level compared the existing explainable methods. In addition, a scheme to enhance the adversarial robustness of CNN models is designed based on the presented explainable approach. The evaluation experiments show that the designed scheme provides an effective way to improve the adversarial robustness of the CNN models, and is a transferable technique in the CNN models that hold different structures.CCS CONCEPTS• Computing methodologies → Object recognition; • Software and its engineering • Software design engineering.
@inproceedings{ZhangWWZC24,
title = {A Pixel-Level Explainable Approach of Convolutional Neural Networks and Its Application},
author = {Haitao Zhang and Jing Wang and Ziyue Wang and Ziyi Zhao and Zhuo Cheng},
booktitle = {ASE},
year = {2024},
doi = {10.1145/3691620.3695320}
}