火力与指挥控制2026，Vol.51Issue(1)：49-55,7.DOI:10.3969/j.issn.1002-0640.2026.01.006
深度神经网络模型鲁棒性测试方法及应用
Robustness Testing Methods and Applications for Deep Neural Network Models
摘要
Abstract
To address the lack of effective robustness testing methods for Deep Neural Network(DNN)models of intelligent systems,this paper first introduces the definition of DNN model robustness,and proposes robustness test evaluation indicators such as disturbance stability and performance fluctuation degree.Then,robustness testing methods for DNN models are proposed from three aspects:noise interference,data distribution and extreme data.Finally,a case application is carried out on the You Only Look Once version 5(YOLOv5)algorithm model for target detection of a certain ground unmanned platform,which verifies the effectiveness and feasibility of the proposed methods.关键词
DNN模型/鲁棒性测试/噪声干扰/极端数据/YOLO算法Key words
DNN models/robustness testing/noise interference/extreme data/YOLO algorithm分类
信息技术与安全科学引用本文复制引用
王栓奇,庞红彪,孟令中,刘钊,武伟..深度神经网络模型鲁棒性测试方法及应用[J].火力与指挥控制,2026,51(1):49-55,7.基金项目
装备预先研究基金资助项目(9090102010206) （9090102010206）
