Click Fraud Detection on the Advertiser Side

Abstract

Abstract. Click fraud-malicious clicks at the expense of pay-per-click advertisers-is posing a serious threat to the Internet economy. Although click fraud has attracted much attention from the security community, as the direct victims of click fraud, advertisers still lack effective defense to detect click fraud independently. In this paper, we propose a novel approach for advertisers to detect click frauds and evaluate the return on investment (ROI) of their ad campaigns without the helps from ad networks or publishers. Our key idea is to proactively test if visiting clients are full-fledged modern browsers and passively scrutinize user engagement. In particular, we introduce a new functionality test and develop an extensive characterization of user engagement. Our detection can significantly raise the bar for committing click fraud and is transparent to users. Moreover, our approach requires little effort to be deployed at the advertiser side. To validate the effectiveness of our approach, we implement a prototype and deploy it on a large production website; and then we run 10-day ad campaigns for the website on a major ad network. The experimental results show that our proposed defense is effective in identifying both clickbots and human clickers, while incurring negligible overhead at both the server and client sides.

Click Fraud Detection and Prevention System for Ad Networks

“…Moreover, current literature is lacking in certain aspects. Many studies focus on the advertiser's side, such as [2], and few on how to apply click fraud detection techniques on ad networks, the middle agent between the publisher and advertiser, all of which are parties involved in the online publicity area (see Section II); and relatively shallow elaboration on the technical details and inner workings of established click fraud detection systems, giving little insight on the design decisions and compromises that went on behind the creation of such applications.…”

“…An example of a PCC method and how it works is in Figure 1. The user visits the publisher's site (1), and then asks for the ad data that's provided by the ad network to the publisher's site (2). The network will proceed by choosing the ad they believe the user is more likely to be interested in (3,4) and sends the data to the user (5).…”

“…Although precise details aren't provided, a good idea of the overall workings of a defense system applied to an agent that's both publisher and ad network is given. Xu et al [2] provide a detailed report on the techniques used for a fraud detection system on the advertiser side, which are key to a better understanding on how one would go about creating similar applications and general detection techniques. However, it is evident the lack of reports on systems that are used by ad networks, and a lack of elaboration on the more technical details and implementations of the tools used to detect and prevent click frauds.…”

Protecting Internet users from becoming victimized attackers of click‐fraud

“…Xu et al proposed a new approach for advertisers to independently detect click‐fraud activities issued by clickbots and human clickers. Their proposed detection system performs 2 main tasks of proactive functionality testing and passive browsing behavior examination.…”

Combating online fraud attacks in mobile-based advertising

“…Another interesting approach is to use bait advertisements [10,13]. Xu et al [14] proposed a systematic approach by introducing additional tests to check whether visiting clients are clickbots.…”