Share on LinkedIn
Share on XOn March 28, 2025, media consultancy Adalytics issued a report that includes unsubstantiated and misleading claims involving Integral Ad Science and our fraud detection. IAS takes these claims and the flawed assessment techniques upon which they’re based very seriously, as we are committed to delivering the advertising industry’s most trusted and transparent media measurement and optimization offerings.
On March 21, we released details of our fraud detection methodology – IAS’s Multi-Tiered Approach to Combating Ad Fraud – to address certain inaccurate claims we heard at that time. We are also continuously evaluating and innovating our offerings to respond to today’s rapidly changing digital landscape.
GIVT and SIVT “bot” traffic:
Legitimate bots like search or large language model (LLM) ‘bots’ are tracked by the IAB in its “Bot User Agent List,” and IAS leverages its list of known spiders and bots to identify benign General Invalid Traffic (GIVT).
Ad fraud bots, otherwise known as Sophisticated Invalid Traffic, or SIVT, are malicious and designed to go undetected. SIVT and other ad fraud schemes are outlined and defined in the IAS Ad Fraud Glossary blog post.
IAS Invalid Traffic technology detects, reports and blocks various types of invalid traffic, including General Invalid Traffic (GIVT) and Sophisticated Invalid Traffic (SIVT). We conduct behavioral analysis using sophisticated machine learning (ML) models and apply a three-pillar approach to fraud detection:
- Rules-based detection with automated rule checks to identify anomalous behavior patterns
- AI/Machine learning that uses big data to detect any hidden, uncommon patterns
- The IAS Threat Lab employs malware analysis and reverse engineering to uncover emerging threats
Paired with the filtering abilities of automated rule-based detection and machine learning technology, plus continuous innovation of the IAS Threat Lab, IAS detects declared and ‘undeclared’ GIVT (as well as SIVT) based on behaviours and other factors. These impressions can be filtered through our pre-bid solutions, and reported on through post-bid measurement, dependent on advertiser customers’ settings. Combating fraud is a shared responsibility across many parties in our ecosystem.
In this context, it is important to note that only IAS and its customers have access to settings configured for their campaigns – including whether or not they are using IAS’ pre-bid IVT avoidance or have chosen to block IVT real-time prior to creative rendering. Accordingly, inaccurate inferences have been made as to whether bots have been “missed”. In addition, in the examples that were provided, IAS’s publisher tag (not IAS’s advertiser tag) was evaluated. Publishers also use our measurement so they can see the same data we report to our buy-side customers. The difference with our primary publisher tag, however, is that, by design, it does not block ads from rendering during post-bid processing.
Additionally, urlscan.io cannot be singled out in all cases as GIVT, as when it is undeclared. Bots originating from urlscan.io from various geo locations are being detected by IAS IVT detection technology as GIVT/SIVT/RVI depending on IP, user agent in conjunction with other signals.
Our commitment to trust and transparency:
At IAS, we constantly innovate to create media measurement and optimization products that help maximize digital ad spend, drive efficiency and deliver real results, as well as protect customers from fraudulent actors. We partner with industry bodies and collaborate closely with our advertiser and publisher customers to continuously improve our solutions.
When it comes to fraud (SIVT) detection:
- Our fraud protection technology is accredited and rigorously assessed in order to achieve that accreditation.
- Our Threat Lab works diligently and proactively to constantly identify new threats and collaborate with partners and the wider industry to address these threats and nullify them, including the recent Vapor Threat scheme identified by our Threat Lab, which resulted in the removal of more than a hundred malicious apps from the Google Play Store.
- Fraud detection by its very nature requires that bad actors do not have access to public information that would allow them to create new threats that could circumnavigate fraud detection technology. That is why we collaborate closely with industry partners and customers to educate and ensure we can try to stay ahead of them.
We are committed to working in partnership with the industry and other companies to reduce the proliferation of bad actors while preserving the open internet.
