In the Threat Lab’s recent Fraud Trends Report, the team advised advertisers and publishers to be wary of ad fraud when it’s at its peak. In the Q4 2023 analysis, the Threat Lab defined October, November, and December as the holiday season — and predicted that these months are particularly dangerous from an ad fraud perspective. The team further anticipated that November, specifically its fourth week, would be the hardest hit by ad fraud.

Now that we can look at global data from the 2023 holiday season, the Threat Lab team wanted to analyze the accuracy of advising caution during this time and understand what this can teach marketers about protecting ad campaigns during particularly turbulent periods.

When is fraud at its highest?

The graph below maps out global ad fraud rates for each day in 2023. The period highlighted in dark green represents the dates between October 12 and December 4, which overlaps with our definition of the holiday season. With a median ad fraud rate 67% greater than the rest of the year, the holiday season stands out as a period of disproportionately high ad fraud activity — so much so that 2023’s highest ad fraud rates all fall within the highlighted period.

What’s the deal with Black Friday?

However, certain dates pop more than others. The graph below shows that ad fraud peaks during November 24, 25, and 26 — also known as 2023’s Black Friday weekend. The median ad fraud of these three days was 36% greater than other dates in the holiday season, and a whopping 122% greater than the rest of the year. The top three most hostile days of 2023 were the Saturday after Black Friday, the Sunday after Black Friday, and Black Friday itself. 

What makes this trend even more peculiar is that November 27, which was the Monday after Black Friday, experienced a 28% decrease in ad fraud relative to the day prior — signaling the highest single day drop of the entire year. This drop suggests that the already disproportionately high holiday ad fraud climaxing on this specific weekend isn’t accidental.

How does fraudulent traffic compare to legitimate traffic?

To understand why the holiday season is so hostile, we compared fraudulent traffic with legitimate traffic.

Although legitimate traffic does increase gradually throughout the year with periodic dips, there aren’t major inconsistencies during the holiday season. Fraudulent traffic, on the other hand, increases dramatically. This comparison suggests that the spike in ad fraud during the holiday season isn’t due to a change in legitimate traffic behavior — it’s linked to fraudulent traffic becoming more active.

So why does this happen? It’s most likely that advertisers aggressively increase their ad spend in the weeks leading up to Black Friday. And once Black Friday ends, they use the remainder of their budget on the following weekend. The challenge with this is that there is a finite supply of high quality inventory available. The increased demand pressures advertisers to buy low quality inventory, exposing their campaigns to higher risk of ad fraud.

How IAS Can Help

When high quality inventory is limited, the risk of fraud infiltrating campaigns is much higher. This risk can be avoided by adopting ad fraud mitigation and protection, which helps keep advertisers from spending their ad dollars on low quality inventory that comes with a higher likelihood of ad fraud.

IAS ensures the most precise fraud detection possible with our three-pillar approach. Our fraud technology is based on a set of methodologies that detect the evolving threat of ad fraud with incredible accuracy. Our approach includes:

• Behavioral and Network analysis: our 10+ billion daily impressions provide a macro view of bot activity
• Browser and Device analysis: real-time signals at the ad call
• Targeted Reconnaissance: malware analysis, software disassembly, and the infiltration of hacker communities guides detection and identification of emerging threats

It’s never too late — or too early — to protect your campaigns from fraud. Be prepared for fraudsters whose activity changes with the seasons. Contact an IAS representative today to find out how to fight fraud and drive superior results.

The post The Threat Lab Analyzes the Year’s Highest Ad Fraud Spikes appeared first on Integral Ad Science.

The post Fraud in Generative AI: A deep dive into how Gen AI affects marketers appeared first on Integral Ad Science.

The post How Does Bot Traffic Vary Over Time? appeared first on Integral Ad Science.

The IAS Threat Lab evaluates fraud in PMP transactions

Marketers widely believe private marketplaces (PMP) create an environment that is resistant, or even immune, to ad fraud. Given the basis for creating a PMP relationship between trustworthy advertisers and publishers, it seems like this could be the case. Unfortunately, the inherent flaws in programmatic open marketplaces still manage to trickle down to PMP transactions.

What is a PMP?

A private marketplace is a digital marketplace where programmatic advertising transactions can take place between trusted and exclusive parties. Within PMPs, a publisher can invite an advertiser to participate in a private auction that occurs in a Real-Time Bid (RTB) environment. PMPs are essentially a programmatic relationship between a publisher and one or more advertisers, attempting to create a clean and trusted environment for premium ad space to be bought and sold.

PMPs are like a hybrid between traditional direct buying and programmatic. The open-ended nature of the auction is reduced by limiting the crowd of buyers. On the flip side, the benefits of RTB environments are still leveraged in order to facilitate an automated and seamless bidding process.

Why should advertisers use a PMP?

The use of PMPs has advantages and disadvantages. On the upside, advertisers can ensure they are paying for premium inventory on trusted publishers and inventory slots can be hand-picked for maximum consumer impact. Plus, along with the benefits of both programmatic and direct buying, content suitability and viewability metrics are assured to be positive—and fraud avoidance is also a likely result.

On the other hand, participation for advertisers in PMPs comes at a premium price point. PMPs also require significant manual interaction and are more time consuming than an open exchange, and there’s no guarantee of ad relevance or having a captive audience.

The assumption is that PMPs assure that advertisers can purchase premium inventory (albeit at premium costs), have their ads prominently displayed adjacent to appropriate content with positive viewability metrics, and lack typical fraud generating behavior.

Due to the benefits of brands being able to protect their reputations with more meaningful ad placements, PMPs have significantly grown in usage in recent years. This is why it is even more crucial to get to the core of the “fraud-free” assumption and understand what’s really at stake beyond placement.

The truth behind fraud in PMPs

To put it simply, PMPs can’t completely prevent fraud. Having evaluated IAS PMP data since the beginning of 2023, we discovered that PMP fraud occurs about 19% as often as it does on an open exchange, indicating there is truth to a lower volume of fraud comparatively. However, we also noted that the CPMs of fraudulent PMP transactions were consistently about 6% higher than they were for non-fraudulent PMP transactions. 

While there’s certainly something to be said about a reduced fraud rate in PMPs, fraud actors are clearly aiming for higher CPMs with specific targeting of PMP transactions.

How could this be the case? Unsurprisingly, it all comes back to the thorn in every advertiser’s side: Bots. While the relationship between the advertiser and publisher may be trusted, this still does not prevent bots from eating up impressions by “visiting” any given domain. Plus, even trusted publishers may source traffic — and if that source hasn’t been fully vetted, it’s highly likely to contain fraudulent traffic.  And a universal truth is that benign bots (or general invalid traffic) are mostly welcomed for services like SEO and indexing, which creates a significant volume of invalid impressions in PMPs, leading to direct losses for advertisers who participate in PMPs as a substitute for ad verification.

In addition to the significant portion of general invalid traffic in PMPs, we also noted a wide array of sophisticated invalid traffic, like user-agent spoofing, device spoofing, geo spoofing, and anomalous behavioral deviation.

By correlating these factors, we were also able to identify likely cohesive botnet traffic, indicating concerted efforts of fraud.

What can you do to avoid PMP fraud?

That’s where IAS can help. Our unique three-pillar approach uses machine learning and unmatched scale to provide the most accurate detection and prevention while most solutions rely on a simple automated check. The industry-leading fraud detection technologies offered by IAS continue to attract significant investment from marketers.

IAS captures up to 280 billion interactions daily from around the world, and trillions of data events are measured each month globally. We provide real-time fraud prevention for programmatic buys with pre-bid targeting segments that leverage MRC-accredited fraud technology. To learn more about our fraud prevention solutions, contact your IAS representative.

The post The State of Fraud in Private Marketplaces appeared first on Integral Ad Science.

The post IAS Threat Lab collaborates with Google to take down malicious app appeared first on Integral Ad Science.

The post Meet the IAS Threat Lab Team appeared first on Integral Ad Science.

Looking for a technical deep dive? Skip ahead to our Methodology for a full breakdown of these results.

Last month, the IAS Threat Lab released our report on the 404bot, a domain-spoofing, malicious bot that we caught with our sophisticated fraud-detection technologies. While we’re glad to have discovered 404bot, the truth is that not all bots are bad. Some bots help put our technology to the test to ensure our bot detection and mitigation continues to be best in class.

Enter: Wombles.

The IAS Data Science Team has been working since late 2019 to perfect Wombles, a crawling bot that allows us to objectively measure the amount of invalid traffic that IAS technology blocks — and how the technology of our closest competitor stacks up. In fact, Wombles lives entirely outside of the IAS Threat Lab as an additional testing mechanism for our own technology, with no connection to our fraud product. Previously, Wombles was used as a brand safety training bot, but our engineers realized he made a great tester for bot traffic, as well. Rest assured, Wombles isn’t just some picture-perfect solution that we engineered to prove our point. As you’ll see shortly, even our technology wasn’t able to catch it immediately, as our models hadn’t been pre-trained to detect its behavior. However, the dynamic learning nature of our tech kicked-in quickly and Wombles didn’t stand a chance.

How does Wombles work? It functions as a pressure test for verification and firewall technologies that underlie IAS and competitive products. By placing Wombles, a relatively unsophisticated bot, on the same inventory and measuring whether it is flagged as valid or invalid traffic, we can determine the difference between IAS and our competitors. (Note: all bot traffic detection should be advanced enough to catch a bot like Wombles which is tasked with doing standard things such as mechanically visiting pages, scrolling around, and using a set of residential IPs to display human behavior.) Think of Wombles as a detective – helping us fight bot traffic by constantly challenging our bot mitigation technology and trying to outsmart it. Below, we can see the results of Wombles pressure testing IAS tech as well as that same pressure test for one of our competitors:

*Please note: Figures are based on monthly projections

These side-by-side graphics show clearly that IAS has a higher cumulative block rate, by a very long way, which means more protection and less wastage of ad spend on bots who don’t shop. But blocking more doesn’t always mean blocking better: under-sophisticated and over-cautious fraud strategies can cause you to miss out on safe, high-value impressions.

In order to conduct the most accurate comparative study, we have to factor out the human traffic that some of our overzealous competitors often flag incorrectly as fraud. The best way to make this distinction is by using a combination of deterministic bot mitigation combined with dynamic machine learning tactics, a pairing that is unique to IAS. Wombles works perfectly to judge this contest because it is a machine itself, so it mimics the behavior of malicious bots and provides a control for the human traffic that often inflates the results of these studies. The data above shows that as IAS models detect and learn from bot traffic schemes like Wombles, they’re able to drastically outperform models that don’t utilize machine learning in their tactics.

[Learn more about machine learning and the  three pillars of ad fraud detection.]

__________________

The result? Across the board, IAS technology identified Wombles and began blocking the crawler within the first few hours of deployment. Competitor B, on the other hand, never blocked Wombles, clearly not using any dynamic machine learning.

__________________

Looking to learn more? We ran our study across 5 different industry verticals and found that an average of 90.8% more bot traffic was identified by IAS tech:

• Automotive 
• Consumer Packaged Goods (CPG) 
• Finance
• Pharmaceutical
• Retail

*Please note: Figures below are all based on monthly projections

If you would like to skip the vertical breakdown, click here to download the full methodology and request a meeting with IAS.

Auto

CPG

Finance

Pharma

Retail

Thanks to the good work of Wombles, IAS is moving the industry toward a more transparent, better-protected future.

If you’re interested in reviewing the full methodology of the study, fill out the form below.

P.S. – Our findings are not limited to bot traffic. Select the checkbox in the below form to request a meeting with IAS for a personalized brand presentation. Discover how IAS can help you reduce wastage from fraud and protect your brand from unsafe content.

The post The IAS “Stop the Bot” Challenge appeared first on Integral Ad Science.

Spotted in early 2018, this scheme is rooted in domain spoofing activities — the fake URLs are not easily detectable to the human eye. The bot is focused on targeting large and, more importantly, out-of-date Ads.txt files. The implementation of Ads.txt by publishers thus far has shown a dramatic decline in bad actors being able to abuse the ecosystem, but fraudsters are constantly evolving, and are now able to capitalize on unaudited Ads.txt files.

Thanks to our Threat Lab’s diligence, we were able to identify the sophisticated 404bot, and ensure that our clients, and the industry as a whole, are protected from the effects. It is crucial to continuously audit and update Ads.txt files to mitigate the 404bot threat.

If you have questions as to whether your campaigns were affected, please reach out to your IAS representative. Read more about the 404bot.

The post Have you seen this bot? appeared first on Integral Ad Science.