DeepSI:A Sensitive-Driven Testing Samples Generation Method of Whitebox CNN Model for Edge Computing  

作　　者：Zhichao Lian Fengjun Tian 

机构地区：[1]School of Cyber Science and Engineering,Nanjing University of Science and Technology,Nanjing 210094,China

出　　处：《Tsinghua Science and Technology》2024年第3期784-794,共11页清华大学学报（自然科学版（英文版）

基　　金：supported by the National Key R&DProgram of China(No.2021YFF0602104-2)。

摘　　要：In recent years,Deep Learning(DL)technique has been widely used in Internet of Things(IoT)and Industrial Internet of Things(IIoT)for edge computing,and achieved good performances.But more and more studies have shown the vulnerability of neural networks.So,it is important to test the robustness and vulnerability of neural networks.More specifically,inspired by layer-wise relevance propagation and neural network verification,we propose a novel measurement of sensitive neurons and important neurons,and propose a novel neuron coverage criterion for robustness testing.Based on the novel criterion,we design a novel testing sample generation method,named DeepSI,which involves definitions of sensitive neurons and important neurons.Furthermore,we construct sensitive-decision paths of the neural network through selecting sensitive neurons and important neurons.Finally,we verify our idea by setting up several experiments,then results show our proposed method achieves superior performances.

关 键 词：neuron sensitivity Layer-wise Relevance Propagation(LRP) neural network verification deeplearning testing 

分 类 号：TP393.09[自动化与计算机技术—计算机应用技术]