An entropy-based methodology for detecting Online Advertising Fraud at scale

Abstract

Programmatic online advertising allows advertisers to di- versify their budget dynamically, set the desired context of publishers content, and target a specific audience. Besides, it is accessible to all budgets. Despite these notable benefits, programmatic advertising has the drawback of being highly exposed to fraud.

The detection of fraudulent activities is a difficult task due to the limited information exchanged between ad-networks and the large volume of publishers and traffic sources (IPs). In general, identifying participants in ad-fraud requires a large effort, while recreating a fraudulent system from different IPs targeting new publishers is relatively easy.

In this paper, we propose an efficient and scalable solution to deterministic ad-fraud. The traffic patterns of ad-fraud bots can be identified using the concept of entropy from information theory. We develop a normalized entropic score to identify the domains involved in ad-fraud and the IPs from which the ad-fraud bots operate. We also describe a lightweight and scalable modular system for fraud mitigation that allows not only to filter out evident fraud, but also configure diffeerent levels of suspicious activity.

Given the complexity of evaluating the potential fraud, the system is configurable letting advertisers to decide the level of risk they are willing to take. As reducing the risk involves increasing the number of false positives, we propose a multi-level scheme with a bank of bloom filters with different price limits to soften the trade-off.