Scholarlink

<p>The rise of blockchain technology has accelerated the development of decentralized applications (DApps), bringing user and network security threats. Efficient decentralized application (DApp) identification is essential for safeguarding user privacy and ensuring blockchain network stability. However, the similarity in communication interfaces and traffic encryption complicates classification. Existing methods also face limitations in feature processing and extraction, leading to lower accuracy. To address these challenges, this paper presents TGAC (traffic graph adaptive convolutional neural network), a DApp identification method based on a graph adaptive convolutional neural network. The method constructs traffic topology graphs by leveraging temporal traffic data, and designs a GAC (graph adaptive convolutional neural network) model to extract key information. It learns local node representations through graph convolution layers and introduces adaptive weights to enhance node features. The method’s effectiveness was validated using a real decentralized encrypted traffic dataset, achieving a classification accuracy of 99.4%, representing a 5% improvement over existing methods.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

TGAC: traffic graph adaptive convolutional neural network-based decentralized application encrypted traffic classification

  • 期刊论文

  • 发表日期：

    2025年5月30日

查看全文
  • Chunni Ren,
  • Jinsong Wang,
  • Zening Zhao

摘要

The rise of blockchain technology has accelerated the development of decentralized applications (DApps), bringing user and network security threats. Efficient decentralized application (DApp) identification is essential for safeguarding user privacy and ensuring blockchain network stability. However, the similarity in communication interfaces and traffic encryption complicates classification. Existing methods also face limitations in feature processing and extraction, leading to lower accuracy. To address these challenges, this paper presents TGAC (traffic graph adaptive convolutional neural network), a DApp identification method based on a graph adaptive convolutional neural network. The method constructs traffic topology graphs by leveraging temporal traffic data, and designs a GAC (graph adaptive convolutional neural network) model to extract key information. It learns local node representations through graph convolution layers and introduces adaptive weights to enhance node features. The method’s effectiveness was validated using a real decentralized encrypted traffic dataset, achieving a classification accuracy of 99.4%, representing a 5% improvement over existing methods.