DeepLogic:Priority Testing of Deep Learning Through Interpretable Logic Units  

作　　者：Chenhao LIN Xingliang ZHANG Chao SHEN 

机构地区：[1]Faculty of Electronic and Infomation Engineering,Xi’an Jiaotong University,Xi’an 710049,China

出　　处：《Chinese Journal of Electronics》2024年第4期948-964,共17页电子学报（英文版）

基　　金：National Key Research and Development Program of China (Grant No. 2020AAA0107702);National Natural Science Foundation of China (Grant Nos. 62006181, 62161160337, 62132011, U21B2018, U20A20177, and 62206217);Shaanxi Province Key Industry Innovation Program (Grant No. 2021ZD LGY01-02)。

摘　　要：With the increasing deployment of deep learning-based systems in various scenes, it is becoming important to conduct sufficient testing and evaluation of deep learning models to improve their interpretability and robustness. Recent studies have proposed different criteria and strategies for deep neural network(DNN) testing.However, they rarely conduct effective testing on the robustness of DNN models and lack interpretability. This paper proposes a new priority testing criterion, called DeepLogic, to analyze the robustness of the DNN models from the perspective of model interpretability. We first define the neural units in DNN with the highest average activation probability as “interpretable logic units”. We analyze the changes in these units to evaluate the model's robustness by conducting adversarial attacks. After that, the interpretable logic units of the inputs are taken as context attributes, and the probability distribution of the softmax layer in the model is taken as internal attributes to establish a comprehensive test prioritization framework. The weight fusion of context and internal factors is carried out, and the test cases are sorted according to this priority. The experimental results on four popular DNN models using eight testing metrics show that our DeepLogic significantly outperforms existing state-of-the-art methods.

关 键 词：Deep learning testing Interpretable logic units Adversarial test Model interpretability Defect detection 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]