计算机与现代化Issue(5)：55-60,6.DOI:10.3969/j.issn.1006-2475.2024.05.010
基于代价敏感卷积神经网络的加密流量分类
Cost-sensitive Convolutional Neural Network for Encrypted Traffic Classification
摘要
Abstract
This paper addresses classification bias and low recognition rates for minority classes in encrypted traffic classification arising from imbalanced data.Traditional convolutional neural networks tend to favor the majority class in such scenarios,prompting a dynamic weight adjustment strategy.In this approach,during each training iteration,sample weights are adaptively adjusted based on feedback from the cost-sensitive layer.If a minority class sample is misclassified,its weight increases,urging the model to focus on such samples in future training.This strategy continually refines the model's predictions,enhancing minor-ity class recognition and effectively tackling class imbalance.To prevent overfitting,an early stopping strategy is employed,halt-ing training when validation performance deteriorates consecutively.Experiments reveal that the proposed model significantly ex-cels in addressing class imbalance in encrypted traffic classification,achieving accuracy and F1 scores over 0.97.This study presents a potential solution for encrypted traffic classification amidst class imbalance,contributing valuable insights to network security.关键词
卷积神经网络/代价敏感学习/加密流量分类/类不平衡/损失函数Key words
convolutional neural network/cost-sensitive learning/encrypted traffic classification/class-imbalance/loss function分类
信息技术与安全科学引用本文复制引用
钟海龙,何月顺,何璘琳,陈杰,田鸣,郑瑞银..基于代价敏感卷积神经网络的加密流量分类[J].计算机与现代化,2024,(5):55-60,6.基金项目
江西省网络空间安全智能感知重点实验室开放基金资助项目(JKLCIP202206) （JKLCIP202206）
