Web Tracking Site Detection Based on Temporal Link Analysis
Web Tracking Site Detection Based on Temporal Link Analysis
复制标题
DOI：
10.2197/ipsjjip.19.62
复制
发表时间：
2010-04
期刊：
影响因子：
--
通讯作者：
A. Yamada;Hara Masanori;Yutaka Miyake
中科院分区：
文献类型：
--
作者：
A. Yamada;Hara Masanori;Yutaka Miyake
网络跟踪网站或网络错误是对用户在网络浏览期间隐私的潜在但严重的威胁。网站及其相关的广告网站秘密地收集访问者的个人资料，并可能滥用或不适当地暴露他们，即使访问者没有自觉地提供他们的个人资料。为了防止公司网络中的此类活动，大多数公司采用依赖于黑名单的过滤器，然而，这些名单是不够的。在本文中，我们提出了Web跟踪站点检测和黑名单生成的时间链接分析的基础上。我们的建议分析网络网关的流量，以便它可以监控管理网络中的所有跟踪站点。该算法在站点及其访问时间之间构建一个图，以表征每个站点。然后，系统使用机器学习算法对可疑站点进行分类。我们确认，62-73%的黑名单网站被检测到的拟议系统，96%的未列入名单的网站是未知或可疑的跟踪网站。
Web tracking sites or Web bugs are potential but serious threats to users' privacy during Web browsing. Web sites and their associated advertising sites surreptitiously gather the profiles of visitors and possibly abuse or improperly expose them, even if visitors do not provide their profiles consciously. In order to prevent such activities in a corporate network, most companies employ filters that rely on blacklists, however, these lists are insufficient. In this paper, we propose Web tracking sites detection and blacklist generation based on temporal link analysis. Our proposal analyzes traffic at the network gateway so that it can monitor all tracking sites in the administrative network. The proposed algorithm constructs a graph between sites and their visited time in order to characterize each site. Then, the system classifies suspicious sites using machine-learning algorithms. We confirm that 62-73% blacklisted sites are detected by the proposed system, and 96% of unlisted sites are unknown or suspicious tracking sites.