收藏切换
Malicious Domain Detection Technology Based on Semantic Graph Learning
收藏切换
Hao Fu1, 2, Chun Long1, 2, Liangyi Gong1, 2, Jinxia Wei1, 2, Pan Huang1, Yanzhong Lin3, Degang Sun1, 2, *
Journal of Computer Research and Development | 2025, 62(9) : 2298 - 2314
Less
收藏切换
Journal of Computer Research and Development | 2025, 62(9): 2298-2314
• Network and Information Security •
Malicious Domain Detection Technology Based on Semantic Graph Learning
Full
Hao Fu1, 2, Chun Long1, 2, Liangyi Gong1, 2, Jinxia Wei1, 2, Pan Huang1, Yanzhong Lin3, Degang Sun1, 2, *
Affiliations
  • 1Computer Network Information Center, Chinese Academy of Sciences, Beijing 100083
  • 2University of Chinese Academy of Sciences, Beijing 101408
  • 3Coremail, Guangzhou 510006
  • born in 1999. PhD candidate. His main research interests include malicious domain name detection, network traffic analysis, and machine learning

    born in 1979. PhD, senior engineer, PhD supervisor. Member of CCF. His main research interests include artificial intelligence based network unknown attack detection, malicious domain name detection, and network traffic analysis

    born in 1987. PhD, senior engineer, master supervisor. Member of CCF. His main research interests include network attack detection, malicious domain name detection, Web attack analysis, and machine learning

    born in 1987. PhD, senior engineer, master supervisor. Her main research interests include artificial intelligence-based network unknown attack detection, malicious domain name detection, and network traffic analysis

    born in 2000. Bachelor, engineer. His main research interests include Web attack detection, penetration testing, and malicious domain name analysis

    born in 1973. Master, vice president of Coremail Technology. His main research interests include email scaling and anti-phishing emails

    born in 1970. PhD, senior engineer, PhD supervisor. His main research interests include communication security, network architecture, and network and system security

About Author:

born in 1999. PhD candidate. His main research interests include malicious domain name detection, network traffic analysis, and machine learning

born in 1979. PhD, senior engineer, PhD supervisor. Member of CCF. His main research interests include artificial intelligence based network unknown attack detection, malicious domain name detection, and network traffic analysis

born in 1987. PhD, senior engineer, master supervisor. Member of CCF. His main research interests include network attack detection, malicious domain name detection, Web attack analysis, and machine learning

born in 1987. PhD, senior engineer, master supervisor. Her main research interests include artificial intelligence-based network unknown attack detection, malicious domain name detection, and network traffic analysis

born in 2000. Bachelor, engineer. His main research interests include Web attack detection, penetration testing, and malicious domain name analysis

born in 1973. Master, vice president of Coremail Technology. His main research interests include email scaling and anti-phishing emails

born in 1970. PhD, senior engineer, PhD supervisor. His main research interests include communication security, network architecture, and network and system security

Published: 2025-09-01 doi: 10.7544/issn1000-1239.202440375
Outline
收藏切换

Malicious domain name detection is a critical component of network intrusion detection systems, enabling the rapid identification of network attacks through domain name requests. Machine learning methods overcome the limitations of blacklist mechanisms and improve detection accuracy. However, challenges such as the high variability of domain name structures and the complexity of real-world environments lead to low detection efficiency and poor robustness in practical applications. To address these issues, a malicious domain name detection technology based on domain name semantic graph learning is proposed, leveraging semantic graph association analysis for efficient detection. Specifically, 12 months of domain request data from China Science and Technology Network are first collected, encompassing 3.33 billion access records, including more than 6.5 million malicious domain name entries across 284 attack types. Semantic analysis reveals significant differentiation between domain categories, yet considerable feature overlap in certain regions degrades classifier performance. To tackle this, a domain association graph model based on character-level semantic similarity is proposed. By integrating features of neighboring domains, the model enhances semantic representations in overlapping regions, thereby improving detection performance. The method includes filtering noise characters through structural similarity analysis, constructing a dynamic domain semantic graph using an online aggregation algorithm, and training a multi-head attention-based message-passing graph model with node-degree-weighted samples. Finally, a multi-layer neural network classifier is employed for malicious domain detection. Experimental results demonstrate that the proposed method achieves an average precision rate of 0.96 and a recall rate of 0.97 on the dataset of different types of malicious domain names. Furthermore, the model exhibits strong online adaptability, achieving high detection rate and robustness.

malicious domain  /  semantic graph learning  /  attention mechanism  /  graph neural network  /  self-evolution
付豪, 龙春, 宫良一, 魏金侠, 黄潘, 林延中, 孙德刚. 基于语义图学习的恶意域名检测技术. 计算机研究与发展, 2025 , 62 (9) : 2298 -2314 . DOI: 10.7544/issn1000-1239.202440375
Hao Fu, Chun Long, Liangyi Gong, Jinxia Wei, Pan Huang, Yanzhong Lin, Degang Sun. Malicious Domain Detection Technology Based on Semantic Graph Learning[J]. Journal of Computer Research and Development, 2025 , 62 (9) : 2298 -2314 . DOI: 10.7544/issn1000-1239.202440375
Year 2025 volume 62 Issue 9
126
59
Cite this Article
BibTeX
Article Info
doi: 10.7544/issn1000-1239.202440375
  • Receive Date:2024-05-31
  • Online Date:2026-11-10
  • Published:2025-09-01
Article Data
Affiliations
History
  • Received:2024-05-31
  • Revised:2025-02-10
  • Accepted:2025-03-03
Affiliations
    1Computer Network Information Center, Chinese Academy of Sciences, Beijing 100083
    2University of Chinese Academy of Sciences, Beijing 101408
    3Coremail, Guangzhou 510006
References
Share
https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202440375
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT