Scholarlink

Botnet represents a persistent threat with significant implications for information systems on the Internet. In this study, we focus on the classification of DGA botnet, which is essential for identifying infected DGA botnet types to implement corresponding preventive measures. We propose a solution based on the BERT large language model and transfer learning. Experimental results on the UMUDGA and UTL_DGA22 datasets show that the proposed solution has at least 9.14% higher accuracy than solutions based on machine learning and 2.03% with popular deep learning models. The above results show the suitability of the proposed solution, which is the basis for developing new solutions in the future.

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

Enhancing DGA Botnet Classification Based on Large Language Models and Transfer Learning

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Tong Anh Tuan,
  • Nguyen Van Truong,
  • Nguyen Thi Uyen,
  • Tran Xuan Sang,
  • Hoang Viet Long

摘要

Botnet represents a persistent threat with significant implications for information systems on the Internet. In this study, we focus on the classification of DGA botnet, which is essential for identifying infected DGA botnet types to implement corresponding preventive measures. We propose a solution based on the BERT large language model and transfer learning. Experimental results on the UMUDGA and UTL_DGA22 datasets show that the proposed solution has at least 9.14% higher accuracy than solutions based on machine learning and 2.03% with popular deep learning models. The above results show the suitability of the proposed solution, which is the basis for developing new solutions in the future.