加密
计算机科学
判别式
联营
数据挖掘
特征提取
预处理器
人工智能
编码器
交通分类
钥匙(锁)
卷积神经网络
特征(语言学)
稳健性(进化)
互联网流量
二进制数
入侵检测系统
模式识别(心理学)
自编码
机器学习
混淆
互联网
计算机网络
利用
掉期(金融)
流量分析
人工神经网络
信息隐私
恶意软件
深包检验
卷积(计算机科学)
分类器(UML)
支持向量机
二进制代码
二元分类
作者
Zongbao Wang,Juan Fu,Zhili Ma,Zhiru Li,Mingming Xiang
出处
期刊:
日期:2026-01-23
卷期号:: 104-108
标识
DOI:10.1109/iccece69169.2026.11399795
摘要
With the widespread adoption of encryption technologies, an increasing proportion of Internet traffic is encrypted, which fundamentally weakens traditional traffic inspection mechanisms. Existing port-based and payload-based detection methods have become ineffective, while approaches relying on handcrafted features suffer from limited discriminative capability and poor generalization. To address the problem of malicious encrypted traffic identification, this paper proposes a lightweight hybrid model named NetFlowClassifier, together with a targeted data preprocessing pipeline. An encrypted traffic dataset is first constructed from CSE-CIC-IDS2018 for binary classification of benign and malicious flows. The proposed model integrates multi-scale depthwise separable convolution and an improved Transformer encoder to jointly capture local discriminative patterns and long-range dependencies. In addition, learnable feature position encoding and attention-weighted pooling are introduced to enhance feature representation. Experimental results show that NetFlowClassifier achieves an F1-score of 0.9661, outperforming baseline CNN and Transformer models by 1.8%–3.2%. With 11.2 million parameters and a throughput of 128 samples per second, the model effectively balances detection accuracy and computational efficiency. These results demonstrate the effectiveness of the proposed approach for malicious encrypted traffic detection in modern network environments.
科研通智能强力驱动
Strongly Powered by AbleSci AI