CT-ER: Detecting Click Fraud in Pay-Per-Click Streams of Online Advertising Networks

随着互联网的快速发展，在线广告在广告市场中扮演着越来越重要的角色，已经成为一项价值10亿美元的业务(2007年达到195亿美元)。目前广泛使用的在线广告收入模式之一是按点击付费(PPC)，即根据关键词的受欢迎程度和竞争广告商的数量对每次点击收费。然而，点击付费模式为个人或竞争对手公司留下了产生虚假点击(即点击欺诈)的空间，因为在购买力平价请求中缺乏可验证的参与度。有报道称，在网络广告市场上，14.6%的人被支付给点击欺诈，这损害了网络广告的发展和健康。该项目正在(1)开发一个全新的可验证点击框架和定义点击质量的新方法；以及(2)开发基于过滤的工具，用于验证和剔除可疑点击，每个工具都提供对误报和负率的量化保证，同时涉及合理的处理开销和空间要求。新的框架提高了广告商和在线广告企业之间的透明度和信任度，并消除了保持点击过滤器的需要。作为商业秘密。还在开发一套便携式课程材料，以促进在本科生和研究生课程中教授已开发的技术。其中一些结果计划被授权给在线广告企业使用。

With the rapid growth of the Internet, online advertisement plays a more and more important role in the advertising market and has become a billion-dollar business ($19.5 billon in 2007). One of the current and widely used revenue models for online advertising is Pay-per-click (PPC), which involves charging for each click based on the popularity of keywords and the number of competing advertisers. However, the pay-per-click model leaves room for individuals or rival companies to generate false clicks (i.e., click fraud) due to the lack of verifiable engagement in PPC requests. It has been reported that in online ad market, 14.6% are paid to Click Fraud, which has damaged the development and healthiness of online advertising. This project is (1) developing a fundamentally new framework for verifiable clicks and a new way of defining the quality of clicks; and (2) developing filtering-based tools for validating and weeding out suspicious clicks, each of which provides quantifiable guarantees on false positive and negative rates while involving a reasonable processing overhead and space requirements. The new framework promotes transparency and trust between advertisers and online ad businesses and eliminates the need for keeping ?click filters? as trade secrets. A set of portable course materials is also being developed to facilitate the teaching of developed techniques in undergraduate and graduate courses. Some of these results are planned to be licensed for use by online ad businesses.