Scholarlink

<p>The growing threat of darknet-related activities, ranging from illegal marketplaces to command-and-control infrastructures, has made the accurate identification of darknet traffic a critical concern for cybersecurity professionals. In response to the lack of high-quality, well-labeled datasets in this domain, we present a newly created dataset of darknet traffic to support research and analysis efforts in network security. The dataset was developed to address data availability, consistency, and challenges with labeling accuracy. It comprises (360,358) normal traffic flows and (91,404) darknet flows in the first layer, along with (26,284) Freenet, (25,499) ZeroNet, (22,958) I2P, (12,546) Tor, and (4117) VPN flows in the second layer, and eight behavioral categories in the third layer, including Browsing (33,586), FTP (20,214), Video Streaming (9559), P2P Sharing (9392), Email (7873), Audio Streaming (5953), Chatting (3489), and VOIP (1338) flows, as published in the Mendeley Data Repository. Potential applications include threat intelligence research, network traffic analysis, and testing security tools and policies. The dataset has a comprehensive three-layered label, indicating its relevance and practical utility for understanding darknet traffic behavior in various applications.</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

SafeSurf Darknet 2025: A novel dataset for darknet traffic detection and analysis

  • 期刊论文

  • 发表日期：

    2025年12月29日

查看全文
  • Qasem Abu Al-Haija,
  • Mohammad J. Obaidat,
  • Ibrahim A. Al-Syouf,
  • Yahea F. Awawdeh,
  • Anas E. Masa’deh

摘要

The growing threat of darknet-related activities, ranging from illegal marketplaces to command-and-control infrastructures, has made the accurate identification of darknet traffic a critical concern for cybersecurity professionals. In response to the lack of high-quality, well-labeled datasets in this domain, we present a newly created dataset of darknet traffic to support research and analysis efforts in network security. The dataset was developed to address data availability, consistency, and challenges with labeling accuracy. It comprises (360,358) normal traffic flows and (91,404) darknet flows in the first layer, along with (26,284) Freenet, (25,499) ZeroNet, (22,958) I2P, (12,546) Tor, and (4117) VPN flows in the second layer, and eight behavioral categories in the third layer, including Browsing (33,586), FTP (20,214), Video Streaming (9559), P2P Sharing (9392), Email (7873), Audio Streaming (5953), Chatting (3489), and VOIP (1338) flows, as published in the Mendeley Data Repository. Potential applications include threat intelligence research, network traffic analysis, and testing security tools and policies. The dataset has a comprehensive three-layered label, indicating its relevance and practical utility for understanding darknet traffic behavior in various applications.