.png){kind=icon}
返回
DeepSI: A Sensitive-Driven Testing Samples Generation Method of Whitebox CNN Model for Edge Computing
.png){kind=icon}
OA
AI
DOI：10.26599/TST.2023.9010057.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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.
Keyword:
neuron sensitivity
Layer-wise Relevance Propagation (LRP)
neural network verification
deep learning testing
期刊
T
IF:
3.5
论文数:
987
被引数:
2.5K
机构
暂无机构信息
引用论文
High-resolution seismic reflection profiles from Lake Titicaca, Peru-Bolivia: Evidence for Holocene aridity in the tropical Andes.png)
Geology
GeologyIF0
PREAI
分享收藏
NPC: Neuron Path Coverage via Characterizing Decision Logic of Deep Neural NetworksNPC: 通过表征深度神经网络的决策逻辑实现神经元路径覆盖OAAI
OAAI分享收藏Energy-Efficient Smart Routing Based on Link Correlation Mining for Wireless Edge Computing in IoT基于链路关联挖掘的物联网无线边缘计算节能智能路由
PREAI
分享收藏Hierarchical Adversarial Attacks Against Graph-Neural-Network-Based IoT Network Intrusion Detection System基于图神经网络的物联网网络入侵检测系统分层对抗攻击OAAI
OAAI分享收藏Blockchain-Based Trustworthy Energy Dispatching Approach for High Renewable Energy Penetrated Power Systems基于区块链的高可再生能源渗透电力系统可信能源调度方法
PREAI
分享收藏
查看更多内容