Can Data Mining Compete with Cyber-security Analysis?

By -




Some Adtech vendors are developing in-house solutions for handling ad-fraud. Usually they are recruiting several data-mining experts and try to solve ad fraud using data analysis.

This is a great way to solve the non-sophisticated fraudsters / fraudulent traffic. However, more sophisticated fraudsters know how to create the exact behavior - CTR/CPV/CPI etc. that advertisers are expecting, making it harder to detect fraud with data analysis.

Fraudsters randomize all possible variables such as browsers, operating systems, websites and more.
We heard about fraudster groups that even record keyboards and mouse movements and then 'play' them randomly.

These kind of methods break data-mining models.

In one case, we analyzed data for a customer that had $100k fraud chargeback on the day we first met him. All of his parameters: CPM/CPC/CPI and even User LTV (life time value) seems "by the book" but all of it was pure fraud...

-Zac

Comments

Post a Comment

Popular posts from this blog

Three Apps on Google Play Click on Ads in the Background - Without the User's Knowledge

By -
Image
Ad hackers are becoming more sophisticated in stealing budgets from advertisers. Symantec researchers discovered three malicious apps on Google Play that collected ad revenue by clicking on ads while running in the background. The three apps used three separate techniques: Delayed attacks Self-naming tricks An attack list received from a command and control server [C&C] Each of these techniques is relatively common on their own, but have not been seen together.  You can read the full report from Symantec here . At Protected Media, we've already flagged those apps as bots even before the post from Symantec. Since our technology can identify bots, regardless of the technique used, we were able to protect our clients from these malicious apps. - Zac
Read more

Was Methbot's Financial Impact Grossly Exaggerated?

By -
Image
In late December, the digital security firm White Ops released a report outlining a sophisticated video ad fraud scheme that it estimated was stealing $3 million to $5 million from marketers each day. The report generated an unprecedented amount of media coverage in outlets including CNN, The New York Times and CBS. However, as we at Protected Media were saying right from the start, the report's estimates of the financial impact of fraud were far lower than stated. In the words of Mike Zaneis, president and CEO of the digital ad industry's Trustworthy Accountability Group (TAG): "It was not millions of dollars a day, Not a chance." Click here to read the full article from Ad Age. Zac
Read more

AppNexus Methbot Analysis

By -
Image
Recent numbers on the effect of Methbot that AppNexus published on their blog are pretty aligned with what we see. To view the post, follow this link:  http://blog.appnexus.com/2016/methbot-denied/  ... In fact, we caught this bot on our end long time ago  ... Recently, we also saw its permutation to a new version of the same bot ;)  But yes, the scale is not as high... -Zac
Read more