计算机科学
加密
特征(语言学)
人工智能
特征提取
数据挖掘
入侵检测系统
计算机网络
人工神经网络
传感器融合
融合
密码学
网络安全
钥匙(锁)
机器学习
数据建模
算法设计
电子邮件
模式识别(心理学)
编码(内存)
解码方法
服务器
作者
Xiang Zhang,Tiankui Zhang,Bingrong Wang,Weiqiang Cheng,Yapeng Wang
标识
DOI:10.1109/jiot.2026.3725511
摘要
With the development of emerging network technologies and new network protocols, such as industrial Internet, mobile Internet of Things (IoT), and low-altitude intelligent connection networks, the network environments are becoming increasingly complex, posing a severe challenge to the identification of malicious network traffic. Existing deep learning-based approaches often rely on a single feature modality, making it difficult to fully describe the multidimensional behavior patterns of network traffic, thus limiting their generalization ability. To address this challenge, this article proposes a multimodal feature fusion-based approach for detecting encrypted malicious traffic. The proposed approach treats the packet sequence of network traffic as a text sequence to extract its text modality (TM) features, and stacks the original byte stream as an image to extract its image modality (IM) features. On the one hand, the TM uses an attention mechanism to model the relationships between packets within a flow. On the other hand, the IM employs a segmented Vision Transformer (ViT) to learn communication patterns from byte-level information such as protocol fields. Then, the interflow information and communication pattern information are fused to achieve a deep representation of traffic behavior patterns. In the proposed approach, we design anonymization experiments and corresponding feature extraction strategies to ensure the effectiveness and generalization of the extracted features. Experimental results on five public datasets show that the proposed approach outperforms benchmarks, especially in the task of malicious traffic identification in heterogeneous network environments, with recognition accuracy exceeding 95%.
科研通智能强力驱动
Strongly Powered by AbleSci AI