基于跨域资源访问的浏览器用户追踪  

Browser user tracking based on cross-domain resource access

作　　者：宋宇波 吴天琦 胡爱群 高尚[4] SONG Yubo;WU Tianqi;HU Aiqun;GAO Shang(Jiangsu Key Laboratory of Computer Networking Technology,School of Cyber Science and Engineering,Southeast University,Nanjing 211189,China;Purple Mountain Laboratories,Nanjing 211189,China;National Mobile Communications Research Laboratory,School of Information Science and Engineering,Southeast University,Nanjing 211189,China;Computing Department,Hong Kong Polytheistic University,Hong Kong 999077,China)

机构地区：[1]东南大学网络空间安全学院,江苏省计算机网络技术重点实验室,南京211189 [2]网络通信与安全紫金山实验室,南京211189 [3]东南大学信息科学与工程学院,移动通信国家重点实验室,南京211189 [4]香港理工大学电子计算学系,中国香港999077

出　　处：《清华大学学报（自然科学版）》2021年第11期1254-1259,共6页Journal of Tsinghua University(Science and Technology)

基　　金：国家重点研发计划项目(2020YFE0200600);江苏省网络与信息安全重点实验室(BM2003201)。

摘　　要：近年来,点击欺诈给广告商造成了巨大的经济损失,迫使广告商支付高额费用。为了应对点击欺诈,广告商通常使用用户配置文件来识别用户身份。但是,攻击者可以轻松构建独特的虚拟操作环境,干扰身份的识别。该文提出了PingLoc机制,一种基于跨域资源访问的定位方案,可检测点击欺诈来源。该方案从ping响应延迟序列提取特征构建用户指纹。测试表明,PingLoc所收集的延迟特征是稳定的,用户定位指纹的准确性高达98%。In recent years,click fraud has caused huge economic losses to advertisers.Many advertisers have then used"user profiles"to identify users to eliminate click fraud.However,attackers can easily construct unique virtual operating environments to confuse the identification algorithms.This paper introduces a localization scheme to detect click fraud sources based on cross-domain resource access.This scheme extracts features from a ping response delay series to fingerprint users.Tests show that the delay features collected by this method are stable with a fingerprint localization accuracy of up to 98%.

关 键 词：点击欺诈 多点ping 用户身份识别 攻击者定位 

分 类 号：TN915.08[电子电信—通信与信息系统]