Skip to main content

FraudSensor FAQ

Below you’ll find a list of frequently asked questions (and answers) about FraudSensor. If you have a question that isn’t answered here, please reach out to a HUMAN representative for assistance. We’re always happy to help!

What percentage of my traffic should I tag?

Before you start tagging any traffic, you should work with a HUMAN representative to calculate the correct FraudSensor sampling rate for your unique needs. However, we generally follow these guidelines:

  • If you serve fewer than 10 million impressions per day, you should tag 100% of your traffic.
  • If you serve more than 10 million impression per day but fewer than 2.5 billion impressions per day, you should tag your traffic at a sampling rate that would yield 20 million FraudSensor impressions per day. (For example, if you serve 750 million impressions per day, tagging 2.6% would yield approximately 20 million FraudSensor impressions.)
  • If you serve more than 2.5 billion impressions per day, you should tag your traffic at a sampling rate that would yield 100 million FraudSensor impressions per day. (For example, if you serve 3 billion impressions per day, tagging 3.3% of your traffic would yield approximately 100 million FraudSensor impressions.)

Which detection tag collects the most/strongest signals?

JavaScript tags are FraudSensor’s strongest and most flexible tag type, but they may not be the best choice in all contexts.

For an overview of the different tag types and their uses, consult our Tag Types and Environments guide.

Can you deploy multiple detection tags on a single page?

Yes! If multiple FraudSensor tags are deployed to the same page—for example, if you have multiple subsequent impressions or you're deploying multiple tags on the same pageload (in the case of multiple HUMAN-tagged creatives on one page)—HUMAN will identify these other tags. Once identified, the grouped tags can communicate and associate their data with one another. We use this combined data to reach a comprehensive decision that's consistent across our respective detection tags.

Can you use the same detection tag type across all environments?

We do not recommend taking a “one tag fits all” approach to detection. When choosing detection tags for each ad placement, it’s important to consider which tag will best suit the ad's environment. For example, if an environment supports JavaScript tags, using a pixel tag instead will yield fewer signals and offer less information overall.

For an overview of the different tag types and their uses, consult our Tag Types and Environments guide.

How does FraudSensor handle inline frames?

In order to function properly, FraudSensor’s detection tags should be served with the relevant ad. If an ad is rendered in an inline frame (also known as an iframe), that detection tag should be deployed within the same iframe. Detection tags deployed outside of an iframe can still collect certain signals for ads rendered inside an iframe, but we won’t be able to collect signals related to user interaction (like clicks, mouse movement, and so on).

Sandboxed iframes require the same type of detail as regular iframes but require a specific token. If you're running ads within a sandboxed iframe, please reach out to a HUMAN representative for assistance.

What should I do if I believe that FraudSensor has mistakenly flagged traffic?

If you believe FraudSensor is flagging traffic inaccurately, please reach out to your Technical Account Manager and request a false-positive check. False-positive checks can help determine whether valid traffic is mistakenly being flagged as invalid.

After you’ve requested this review, your Technical Account Manager will work with HUMAN’s Detection team to gather more information and verify the accuracy of your results. Your Technical Account Manager will then help you take further steps as needed.