Product Archives - Integral Ad Science https://integralads.com/insider/category/resources/products/ The Hidden Cost of MFA Webinar Wed, 29 Oct 2025 18:25:06 +0000 en hourly 1 https://wordpress.org/?v=6.8.3 https://integralads.com/wp-content/uploads/2023/06/IAS-Favicon-2023-Square.png Product Archives - Integral Ad Science https://integralads.com/insider/category/resources/products/ 32 32 TikTok Selects IAS for Brand Safety Measurement Across Pangle Advertisers https://integralads.com/insider/tiktok-selects-ias-for-brand-safety-measurement-across-pangle-advertisers/ Tue, 28 Oct 2025 18:00:00 +0000 https://integralads.com/?p=344165 IAS has been selected by TikTok Pangle to launch new brand safety measurement features—alongside viewability and invalid traffic (IVT) measurement—for advertisers on TikTok Pangle, the platform’s global ad network for business.

The post TikTok Selects IAS for Brand Safety Measurement Across Pangle Advertisers appeared first on Integral Ad Science.

]]>

IAS expands partnership with TikTok to deliver trusted transparency and brand protection for advertisers

IAS has been selected by TikTok Pangle to launch new brand safety measurement features—alongside viewability and invalid traffic (IVT) measurement—for advertisers on TikTok Pangle, the platform’s global ad network for business.

Pangle reaches more than 380,000 apps worldwide and connects with 2.9 billion daily active users through app traffic. With this latest integration, advertisers can pair IAS’s AI-driven Total Media Quality (TMQ) for TikTok post-bid measurement with IAS Post-Bid Measurement for TikTok Pangle, unlocking incremental reach and deeper transparency across a vast network of mobile apps.

Strengthening trust and transparency for global advertisers

This collaboration expands on IAS’s existing Social Optimization suite for TikTok, empowering advertisers to measure and optimize campaigns across diverse environments with confidence.

Through IAS Post-Bid Measurement for TikTok Pangle, advertisers gain:

  • Expanded Total Media Quality coverage: Viewability, Invalid Traffic (IVT), and Brand Safety Measurement across TikTok Pangle, in addition to TMQ for TikTok with coverage including TikTok’s For You Feed, Profile Feed, Following Feed, Search Feed, For You Feed and TikTok Lite (in supported markets).
  • Global reach: IAS supports TikTok Pangle advertising inventory spanning across 380,000 apps that reach audiences in the APAC, EMEA, and LATAM regions.
  • Trusted, third-party measurement: Verification that ads running on TikTok Pangle appear alongside brand-safe mobile apps, adhering to industry standards.

Building on a growing TikTok partnership

IAS and TikTok’s collaboration dates back to 2021 with the launch of a pre-bid optimization product, followed by the 2025 expansion of Social Optimization for TikTok to include pre-bid Video Exclusion Lists. This latest milestone demonstrates IAS’s continued commitment to providing end-to-end media quality measurement across the world’s most engaging social and in-app environments.

As the digital ecosystem evolves, IAS remains focused on delivering actionable insights that help advertisers optimize performance, protect brand reputation, and maximize ROI across every screen and platform.

Reach out to an IAS representative today to learn more.

The post TikTok Selects IAS for Brand Safety Measurement Across Pangle Advertisers appeared first on Integral Ad Science.

]]>
Elevating Transparency and Performance with IAS’s Impression Feed https://integralads.com/insider/elevating-transparency-performance-impression-feed/ Fri, 30 May 2025 12:00:00 +0000 https://integralads.com/?p=342246 Advertisers, platforms, and partners alike are demanding clearer insights into where their ads run, how they perform, and what’s driving results. But for too long, much of that clarity has been locked inside the programmatic black box. Enter Impression Feed — addressing the industry’s need for transparency.

The post Elevating Transparency and Performance with IAS’s Impression Feed appeared first on Integral Ad Science.

]]>

As digital advertising grows more complex, the industry’s call for transparency has never been louder. Advertisers, platforms, and partners alike are demanding clearer insights into where their ads run, how they perform, and what’s driving results. But for too long, much of that clarity has been locked inside the programmatic black box.

Enter Impression Feed — addressing the industry’s need for transparency.

Known more broadly as log-level data (LLD) or impression-level data, this level of granularity has become a critical component for media buyers and platforms looking to take ownership of their performance. As ad platforms begin to open up access to this data, advertisers and agencies are eager to put it to work — whether to build in-house optimization tools, power custom bidding models, or unify reporting across platforms.

The challenge? Raw data is only as useful as it is accessible and actionable. That’s where IAS steps in.

Understanding Impression Feed

Transparency, customization, and precision are no longer optional — they’re essential for digital media performance. IAS’s Impression Feed meets these demands head-on by giving advertisers and partners direct access to the most granular level of media quality data available.

What is Impression Feed?

Formerly known as Log-Level Data (LLD), Impression Feed is a powerful data solution that provides 250+ metrics at the individual impression level. Each row of data represents a single impression IAS has measured — allowing advertisers to capture detailed insights for every ad served, across supported formats and environments.

Impression Feed delivers highly granular, impression-by-impression quality metrics across fraud, viewability, brand safety and suitability, geo, as well as other advanced metrics and advanced outcome metrics — offering a clear, customizable dataset designed for both verification and performance – collected and normalized across partners. 

Impression Feed is designed to meet the needs of today’s most data-driven organizations — from advertisers and agencies to platforms and managed service providers. This high-resolution view enables customers to:

  • Build bespoke planning, reporting, and optimization tools
  • Join impression data with campaign, audience, or creative signals
  • Analyze what’s working — at scale and in detail

Impression Feed puts the raw performance data directly in your hands, giving you the freedom to define success on your terms. With two flexible offerings — Standard and Premium — advertisers can select the level of detail that best suits their business needs and optimization goals.

Who benefits from Impression Feed?

Advertisers use Impression Feed to power in-house optimization tools and gain clearer visibility into where and how their media dollars perform. With high-quality data delivered hourly, teams can benchmark success, monitor campaign health, and reallocate spend with confidence.

Agencies often rely on Impression Feed to streamline media planning and reporting. With access to aggregated, structured data, they can feed proprietary algorithms and provide their advertiser clients with richer, insight-driven recommendations.

Publishers use Impression Feed to unlock powerful opportunities to optimize inventory, improve yield, and strengthen advertiser trust. By leveraging granular impression-level data, publishers can refine page layouts, package high-quality inventory into premium deals, and proactively address campaign performance  issues — all with the transparency and credibility of IAS verification.

Platform partners including DSPs and SSPs can use Impression Feed to improve algorithmic buying and inventory curation:

  • DSPs tend to leverage the data to feed custom algorithms, like quality CPM (qCPM) optimization to drive greater performance.
  • SSPs can use Impression Feed to enhance their services and deliver more curated, high-performance inventory packages.

Managed Service Providers (MSPs) integrate IAS data with audience insights to build privacy-safe targeting strategies. By layering keyword signals and contextual intelligence, they deliver more tailored and effective client campaigns.

What data is available in Impression Feed?

Impression Feed includes a comprehensive mix of metrics that span brand safety and suitability, fraud, geo, viewability, and more. Advertisers can choose from a pre-defined set of fields — or work with IAS to build a tailored data schema that aligns with their existing systems and KPIs.

Here’s a breakdown of what’s included in each tier.

Standard Impression Feed: Foundational insights for smarter media strategies

For many teams, media success starts with clarity. The Standard Impression Feed delivers streamlined access to the key metrics needed for day-to-day decision-making and lightweight analytics. This tier is built for advertisers and agencies looking to verify performance, plan future campaigns, and benchmark results using high-quality impression-level data.

The dataset includes 27 core metrics across five categories:

  • Metadata: Ad campaign details, media type, and platform type
  • Fraud: Detection of invalid traffic types
  • Brand Safety and Suitability: Pass/fail results based on IAS standard category settings
  • Geo: Country, state, and DMA-level reporting
  • Viewability: Yes/No viewable flags, plus video quartile completions

Use cases for Standard Impression Feed include:

  • Benchmarking success: Compare campaign performance to peer and industry benchmarks.
  • Quick validation: Run rapid checks to confirm setup accuracy and delivery integrity.
  • Strategic planning: Conduct post-campaign analysis to inform next-year media decisions.
  • Basic performance analytics: Leverage simple metrics like viewability to guide optimizations.

This tier is ideal for advertisers and agencies who need accessible, high-quality data for better control and seamless integration of reporting data into their dashboards/reporting systems.

Go beyond reporting with Premium-level precision

For performance-driven teams, the Premium Impression Feed offers more than transparency — it delivers the infrastructure to build smarter, faster, and more impactful campaigns. With access to enriched impression-level data and customizable metrics, advertisers and partners can go far beyond standard reporting to power in-house models, train AI algorithms, and inform every decision with precision.

Premium includes all Standard fields, plus advanced metrics that enable richer insights, advanced modeling, and deeper optimization:

  • Advanced Metadata: Browser/device details
  • Advanced Fraud: Granular fraud subcategories for detailed risk classification
  • Advanced Brand Suitability: Scores across nuanced content categories like hate speech and violence
  • Advanced Geo: Language signals, time zone, and enhanced location attributes
  • Advanced Viewability: Time-in-view, hover rate, scroll depth, and custom visibility calculations

Together, these fields support a wide range of applications — from audience modeling and AI training to real-time performance tuning.

Here’s how advanced teams are using Premium to unlock performance:

Joinability and enrichment

Premium Impression Feed integrates seamlessly with both first- and third-party datasets. Using joinable identifiers — such as impression ID, DSP Creative ID, URL, Audience ID, or others — advertisers can uncover a more detailed picture of where, how, and why campaigns perform. This opens the door for richer attribution, deeper audience understanding, and full-funnel campaign insights.

Whether it’s analyzing how a specific creative performs across multiple channels or attributing outcomes to individual publishers, joinability enables a more unified, connected data strategy.

Custom metrics control

One size doesn’t fit all when it comes to media measurement. Premium users have the flexibility to define metrics that match their unique business needs, such as custom viewability definitions, refined brand suitability thresholds, or vertical-specific KPIs.

This flexibility helps internal teams align measurement with campaign goals, reduce noise, and focus on what actually drives success.

High-value signals for smarter decisioning

Premium Impression Feed includes IAS’s most sophisticated quality and outcome-based signals. These advanced metrics are designed to help advertisers move from reactive optimization to predictive planning.

  • Attention measurement captures how audiences engage with ads, providing insight into potential impact.
  • qCPM reveals the true cost of effective media, factoring in quality and context rather than just price.
  • Carbon emissions data enables advertisers to track and reduce the environmental impact of their campaigns while maintaining performance goals.

These signals help advertisers go beyond clicks and impressions to optimize for meaningful outcomes.

Always-on enhancements

As part of IAS’s continued investment in data innovation, Premium Impression Feed users gain early access to cutting-edge metrics as they are developed. From contextual intelligence to attention signals and beyond, Premium users are always equipped with the latest tools to stay ahead of the curve.

Built for custom optimization

One of the most powerful features of Impression Feed — specifically with the Premium tier — is its flexibility. Advertisers can build fully customized, in-house solutions by merging IAS signals with their own campaign, audience, or performance data.

Custom tools can be built using impression-level identifiers such as:

  • IAS unique impression ID
  • Ad server or DSP macro values (e.g., custom session IDs, DSP creative IDs)
  • Device-level signals

Looking ahead, IAS will continue to enrich the dataset through 2025 with planned additions including audience and outcomes signals based on advertiser needs. This ensures that teams using Impression Feed today will be well-positioned for the data demands of tomorrow.

Increasing accessibility to Impression Feed

IAS’s Impression Feed is a critical tool for enhancing transparency, precision, and performance — but accessibility is key to taking action on these metrics. That’s why we’ve partnered with Databricks to join their open-source protocol, which enables secure data sharing across platforms without requiring data duplication or movement.

Through this integration, advertisers have the option to access Impression Feed data directly via Databricks without needing to manually ingest raw log files, reducing operational friction and increasing speed and accessibility to insights.

Explore what’s possible with Impression Feed

Impression Feed is more than a reporting tool. It’s a foundation for transparency, trust, and transformation in digital advertising. In a world where data-driven strategy is the baseline, Impression Feed empowers advertisers to go further — fueling smarter decisions, stronger outcomes, and full visibility into every impression that matters.

Whether you’re starting with the Standard offering or building with Premium, our teams are ready to support your goals with a solution tailored to your data needs. 

Contact your IAS representative today to learn more about Impression Feed.

The post Elevating Transparency and Performance with IAS’s Impression Feed appeared first on Integral Ad Science.

]]>
How Advertisers Can Avoid Overblocking During Major Cultural Moments https://integralads.com/insider/how-advertisers-can-avoid-overblocking-during-major-cultural-moments/ Thu, 17 Apr 2025 12:00:00 +0000 https://integralads.com/?p=341346 Every year, major cultural moments like awards season, the Super Bowl, or March Madness generate headlines, social media buzz, and countless opportunities for advertisers to connect with highly engaged audiences.  But overblocking has been an ongoing issue. For example, this...

The post How Advertisers Can Avoid Overblocking During Major Cultural Moments appeared first on Integral Ad Science.

]]>

Every year, major cultural moments like awards season, the Super Bowl, or March Madness generate headlines, social media buzz, and countless opportunities for advertisers to connect with highly engaged audiences. 

But overblocking has been an ongoing issue. For example, this year’s Oscars-related content was often blocked from advertising due to overly restrictive keyword blocklists, causing advertisers to inadvertently cut themselves off from premium inventory.

The consequence of an overreliance on keyword blocklists is twofold: advertisers miss valuable opportunities to engage with audiences, and publishers — especially in the news industry — lose critical ad revenue.

So how can brands strike the right balance, ensuring they remain protected without missing out?

Why major cultural moments matter for brands

Major cultural moments provide a huge opportunity for scale and impact. This year’s Super Bowl, for example, garnered a record breaking 127.7 million viewers, all the while generating widespread buzz across key advertising channels. These “moment in time” events are often as costly as they are critical. The average Super Bowl ad in 2025 cost $8 million for a 30 second spot — and it’s important that these big investments yield big returns.

For advertisers, these events aren’t just about visibility — they’re about impact. They offer a unique chance to align brand messaging with content people are deeply engaged in and emotionally connected to. Whether it’s a highly anticipated film winning Best Picture or a buzzer-beater during March Madness, these moments drive heightened attention and real-time conversation, creating countless opportunities for meaningful ad placements.

The cost of overblocking: What advertisers are missing

For years, keyword blocklists have been the default approach to brand safety. The logic is simple: brands create lists of words associated with risky content — terms like “violence,” “death,” or “shooting” — and prevent their ads from appearing on any pages that include them.

But in practice, this approach is far too blunt.

During the Oscars, for example, entire discussions about critically acclaimed films were off-limits to advertisers. A Best Picture nominee like Emilia Pérez—which tells the story of a cartel boss transitioning to a new life—might trigger blocks due to words like “cartel” or “drugs,” even in the context of positive reviews or industry analysis. The same applies to March Madness coverage: blocking words like “shot” or “shoot” may seem logical for safety reasons, but it also eliminates access to high-interest and timely basketball highlights.

Rethinking brand safety and how to avoid overblocking

Rather than relying on rigid keyword lists, advertisers need a more sophisticated approach that understands the full context of content before deciding whether to block or allow it.

At IAS, we take brand safety beyond single-word exclusions by using AI-powered contextual technology to analyze content at the page level. Instead of automatically blocking a page for containing the word “violence” in the URL, our technology determines the actual context, sentiment, and emotion of the page to understand the true intended meaning.

This level of nuance is essential, especially during major events where engagement is at its peak. When brands use contextual technology rather than static keyword blocklists, they can:

  • Avoid missing out on premium, culturally relevant content while still ensuring ads appear in suitable environments.
  • Ensure greater campaign efficiency, allowing media dollars to work harder by targeting the right audiences at the right moments.
  • Support quality news by enabling trusted news publishers to monetize important stories, rather than inadvertently pushing dollars toward less reputable sources.

The future of brand safety: Smarter, not stricter

Overblocking during major cultural moments isn’t just a missed opportunity — it’s an avoidable mistake. With the right tools, advertisers can stay relevant, maximize reach, and protect their brand without unnecessary restrictions.

As events like the Oscars, Super Bowl, and upcoming cultural events drive public conversations, advertisers have a choice: continue using outdated, overly restrictive blocklists, or embrace a more nuanced, context-driven approach that balances safety with opportunity.

How IAS helps advertisers avoid overblocking without compromising safety

IAS empowers brands to take control of their brand safety and suitability strategies without sacrificing reach or missing critical cultural moments.

With solutions like Context Control, IAS helps brands:

  • Maximize premium inventory during major events: Ensure ads appear alongside high-quality, high-traffic content covering events like the Oscars, Super Bowl, and the Olympics, rather than being unnecessarily blocked.
  • Reduce wasted ad spend: Avoid the inefficiencies of overblocking, keeping campaigns optimized for reach and engagement without running ads in inappropriate contexts.
  • Enhance precision in brand safety and suitability: Instead of blocking pages based on a single word, IAS technology analyzes the full context — differentiating between a movie review, a sports highlight, and genuinely unsafe content.
  • Support trusted news and premium publishers: Advertisers can confidently invest in news and entertainment content, rather than unintentionally funneling budgets to lower-quality environments.
  • Adapt in real-time to emerging cultural moments: As conversations evolve, IAS solutions continuously analyze and adjust, ensuring advertisers remain agile while maintaining brand protection.

IAS’s Context Control is powered by a proprietary cognitive semantic technology that leverages Natural Language Processing (NLP) to extract page semantics, context, emotion, and sentiment. We offer 280+ vertical and topical segments for content avoidance and 370+ vertical, topical, seasonal, and audience proxy segments for targeting. In addition, IAS has the ability to create brand-specific contextual segments for content avoidance.

Rather than taking a black-and-white approach to brand safety, IAS provides the contextual technology needed to make informed, strategic decisions — allowing advertisers to stay relevant, increase engagement, and drive meaningful results without unnecessary restrictions.

The post How Advertisers Can Avoid Overblocking During Major Cultural Moments appeared first on Integral Ad Science.

]]>
Performance & Brand Equity in the New Media Landscape https://integralads.com/insider/performance-brand-equity-new-media-landscape/ Wed, 09 Apr 2025 12:00:00 +0000 https://integralads.com/?p=338813 How advertisers can drive performance and elevate brand reputation in a dynamic media landscape In a digital world where unpredictability is the norm, advertisers face the constant challenge of safeguarding their brand’s reputation — but cost often gets in the...

The post Performance & Brand Equity in the New Media Landscape appeared first on Integral Ad Science.

]]>

How advertisers can drive performance and elevate brand reputation in a dynamic media landscape

In a digital world where unpredictability is the norm, advertisers face the constant challenge of safeguarding their brand’s reputation — but cost often gets in the way. So how can advertisers proactively protect their brands while also prioritizing cost efficiency?

Our latest white paper, Performance & Brand Equity in the New Media Landscape, is a must-read for advertisers looking to improve end-to-end campaign performance and maximize ROI. Backed by real-world case studies, this white paper is your roadmap to simultaneously driving brand equity and cost savings.

Download the white paper now to learn how to:

  • Leverage a proactive approach to brand safety without sacrificing scale
  • Reach more consumers in environments you deem safe and suitable
  • Boost campaign performance and cost savings with Context Control Avoidance

The post Performance & Brand Equity in the New Media Landscape appeared first on Integral Ad Science.

]]>
Supporting News While Ensuring Brand Suitability https://integralads.com/insider/supporting-news-while-ensuring-brand-suitability/ Wed, 09 Apr 2025 11:59:00 +0000 https://integralads.com/?p=341252 In recent months, the industry has pointed to media quality and measurement companies to address how brand safety will unlock greater media spend on news. There’s a perception that brand safety measures limit advertising on news content, inadvertently harming news....

The post Supporting News While Ensuring Brand Suitability appeared first on Integral Ad Science.

]]>

In recent months, the industry has pointed to media quality and measurement companies to address how brand safety will unlock greater media spend on news. There’s a perception that brand safety measures limit advertising on news content, inadvertently harming news. However, brand safety and suitability can and should be an ally to news publishers — not an obstacle.

Traditionally, many advertisers have relied on keyword blocking — an exclusionary approach that prevents ads from appearing alongside specific words or phrases — to manage brand safety risks. While once a widely used method, keyword blocking lacks nuance, as it doesn’t account for context, sentiment, or emotion. This blunt approach can result in overblocking, where brands may miss valuable reach, exclude diverse content creators, and penalize news publishers without truly mitigating risks. Overblocking can be difficult to identify due to keyword blocking oftentimes being implemented in multiple places in the media supply chain (e.g., within DSPs).

Simply avoiding news sites or content containing certain words is a missed opportunity for brands looking to connect with engaged audiences. Consumers actively seek out trusted news sources to stay informed, making it essential for advertisers to adopt more precise, contextual approaches to ensure brand protection without sacrificing scale.

Advertiser Benefits: Maximizing ROI While Safeguarding Brand Reputation

IAS is committed to re-educating the industry and working closely with advertisers, agencies, and publishers to foster a balanced approach that ensures brand protection while supporting a free and sustainable press.

Advertisers don’t have to choose between brand safety and supporting news — IAS enables them to confidently invest in news environments while minimizing risks. Instead of blunt exclusion tactics like excessive keyword blocklists, we provide granular, AI-driven contextual solutions that refine brand suitability preferences rather than eliminating valuable news inventory.

Key IAS Solutions for Advertisers

  • IAS Context Control for Brand Suitability and Contextual Targeting: Uses Natural Language Processing (NLP) to analyze sentiment and emotion across 50+ languages, ensuring advertisers can support news while controlling risk.
    • Historically, some brands have paused media buys entirely in times of uncertainty, heavily penalizing publishers and affecting reach for advertisers. With near real-time contextual classification, IAS gives advertisers the tools to reduce risk without sacrificing reach — especially during moments of rapid change. 
  • Keyword to Contextual Consultation: IAS helps advertisers transition away from static keyword blocklists by recommending dynamic contextual targeting strategies.
  • Allow News Homepages Segments: 29 unique IAS segments that enable advertisers to avoid content across industry-aligned brand safety and suitability concerns without blocking or avoiding news homepages.
  • Industry Standard Content Sub-Category Segments: Across 12 industry standard brand safety categories, advertisers can set different risk tolerance thresholds based on content type, enabling advertisers to calibrate their suitability controls more precisely for news content versus other types of content such as gaming or entertainment.
  • URL Trusted List: Allows advertisers to bypass brand safety filters for pre-approved news publishers.

Why This Matters for Advertisers

  • Reach engaged audiences on trusted news sites, maximizing ROI.
  • Provide transparency into ad placements while ensuring control.
  • Prevent unnecessary overblocking that reduces campaign scale.

Publisher Benefits: Driving Demand While Preserving Inventory Value

From a publisher’s perspective, brand suitability measures should be maximizing revenue while providing suitability. IAS’s transparent solutions enable publishers to better monetize their inventory and optimize yield while preserving advertiser confidence in their inventory. By leveraging advanced contextual controls, publishers can retain monetization for brand-safe content without unnecessary restrictions.

Key IAS Solutions for Publishers

  • Quality Attention for Publishers: Provides publishers and SSPs with actionable insights into inventory quality, helping optimize yield and revenue by highlighting premium, high-attention inventory.
  • MFA and Ad Clutter Protection: Helps direct advertiser demand to premium news by filtering out low-quality MFA (Made-for-Advertising) and ad-cluttered environments. Because our MFA reporting is available to all advertisers, we help reputable publishers stand out and drive better yield. IAS also equips publishers with insights to enhance inventory quality, improve engagement, and drive advertiser confidence. Publishers have access to their own MFA or Ad Clutter scores to gain greater transparency into their inventory, enabling them to optimize and attract higher-value demand.
  • Data-Driven Brand Suitability Enhancements: IAS continuously refines its classification models based on data and insights, as well as feedback from publishers and advertisers, helping ensure high-quality news content remains monetizable.

Why This Matters for Publishers

  • Protect the value of news by ensuring fair access to advertising dollars.
  • Reduce unnecessary blocking that limits inventory yield.
  • Improve buyer confidence and demand for premium news placements.

How IAS News Sub-Categories Support News Monetization

To further reduce the risk of overblocking news while keeping advertisers protected, IAS offers granular contextual categories as part of Context Control that enable advertisers to set different risk thresholds for news content than other content types. Additionally, IAS offers contextual categories that will block risky content but allow all news homepages. News homepages often face overblocking due to the nature of their content, containing many headlines of various topics.

Tools like this help ensure ads serve on trusted news sources while avoiding high-risk content elsewhere. IAS offers 45 news-specific Context Control segments to help advertise on news more effectively — with many at varying risk thresholds aligned to industry standard risk levels. These segmented controls enable advertisers to support reputable news sources while maintaining brand suitability. Additionally, IAS offers sentiment-based segments, enabling advertisers to only block negative content for a given topic as opposed to overblocking the entire topic.

Example in Action

An advertiser may be averse to advertising on any webpage that is related to “crime,” but in the context of news, the advertiser may only want to avoid high risk crime content, or not even block crime on news at all. With our granular contextual categories, the advertiser can easily loosen restrictions to news content versus other content types.

IAS “Allow News Homepages” Segments

These segments give advertisers the control and flexibility to employ different risk thresholds for news. Advertisers can block content across the following categories, without blocking news homepages:

Mythbusters Infographic 3

Strengthening Brand Safety While Supporting News

IAS is committed to fostering a balanced digital ecosystem where advertisers can confidently invest in news while maintaining brand safety.

Through contextual intelligence and publisher-focused solutions, IAS empowers advertisers and publishers alike — ensuring that brand safety remains an enabler of news, not a limitation.

The post Supporting News While Ensuring Brand Suitability appeared first on Integral Ad Science.

]]>
Addressing Claims on IAS’s Fraud Detection Technology  https://integralads.com/insider/addressing-claims-fraud-detection-technology/ Thu, 03 Apr 2025 23:10:42 +0000 https://integralads.com/?p=340770 IAS is committed to delivering the advertising industry’s most trusted and transparent media measurement and optimization offerings, and we will continue to take actions towards protecting customers from fraudulent actors. On March 28, media consultancy Adalytics issued a report containing...

The post Addressing Claims on IAS’s Fraud Detection Technology  appeared first on Integral Ad Science.

]]>

IAS is committed to delivering the advertising industry’s most trusted and transparent media measurement and optimization offerings, and we will continue to take actions towards protecting customers from fraudulent actors.

On March 28, media consultancy Adalytics issued a report containing unsubstantiated and misleading claims about Integral Ad Science and our fraud detection capabilities. That same day, we published a blog post titled “Update: IAS’s Multi-Tiered Approach to Combatting Ad Fraud” to address and clarify these initial inaccuracies. IAS continues to have serious concerns about these claims and the flawed assessment techniques upon which they’re based. 

Upon further analysis and due diligence by our technical teams, the following summary aims to correct misleading claims in the report and provide additional context on how IAS detects and classifies invalid traffic.

Overview of Key Terminology

  • General Invalid Traffic (GIVT) Ads: 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). This is traffic that failed to meet ad quality criteria filtered through and caught by known IP and bot lists (ex: Google web crawlers). GIVT is always invalid traffic.
  • Sophisticated Invalid Traffic (SIVT) Ads:  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. This is traffic that failed to meet proprietary and sophisticated invalid traffic detection criteria. Examples of failed traffic can include: hijacked devices, ad tags, or creative; adware; malware; and misappropriated content. 
  • Reduced Value Inventory (RVI) Ads: Traffic that IAS flagged as being generated in a way counter to the advertiser’s interests. Possible examples include the use of incentivized browsing and “proxy servers.” RVI impressions are flagged in our systems to allow advertisers to evaluate the performance of these impressions. Some impressions that may be initially flagged as RVI may later be flagged as IVT based on our fraud detection.

Findings on the Bots Described

Adalytics calls out three bots: two known (URLScan.io and HTTP Archive) and one unknown (anonymous). These types of bots have constantly shifting IPs underneath them, meaning the bots will work through new IPs on a consistent basis. IAS fraud detection systems are able to identify and classify both URLScan.io and HTTP Archive. 

Addressing the Unsubstantiated and Misleading Claims

Claim 1: IAS treated URLScan.io as valid traffic in 77% of tests.

IAS Response: IAS classified URLScan.io impressions as GIVT, SIVT, or Reduced Value Inventory (RVI). These bots rotate through undeclared and constantly shifting IP addresses. To prevent false positives, our fraud models rely on impression level thresholds to confirm fraud. Once that threshold is met, impressions are blocked and the IPs are incorporated into our fraud solutions.

Claim 2: IAS treated HTTP Archive as valid traffic 16% of the time.

IAS Response: IAS flagged HTTP Archive traffic as GIVT.

Claim 3: IAS publisher tools simultaneously flagged the same impression as both valid and invalid.

IAS Response: External analysis cannot accurately read our backend adjudication. As stated previously, fraud detection by its very nature requires that bad actors or external sources do not have access to public information that would allow them to create new threats which in turn circumnavigate fraud detection technology. That is why we collaborate closely with industry partners and customers to stay ahead of bad actors. 

Claim 4: Publishers served ads to known bots even after they were flagged.

IAS Response: IAS provides the capability to block IVT, but publisher partners choose whether to enforce those blocks. As stated previously, only IAS and its customers have access to settings configured for their campaigns — including whether or not they are using IAS’s pre-bid IVT avoidance or have chosen to block IVT real-time prior to creative rendering. 

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. As always, 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.

You can read more about IAS’s Multi-Tiered Approach to Combating Ad Fraud here.

The post Addressing Claims on IAS’s Fraud Detection Technology  appeared first on Integral Ad Science.

]]>
Update: IAS’s Multi-Tiered Approach to Combating Ad Fraud https://integralads.com/insider/update-ias-multi-tiered-approach-to-combatting-ad-fraud/ Fri, 28 Mar 2025 19:28:15 +0000 https://integralads.com/?p=340684 On 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...

The post Update: IAS’s Multi-Tiered Approach to Combating Ad Fraud appeared first on Integral Ad Science.

]]>

On 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.

The post Update: IAS’s Multi-Tiered Approach to Combating Ad Fraud appeared first on Integral Ad Science.

]]>
Beyond Keywords: IAS’s AI-Driven Contextual Protection https://integralads.com/insider/beyond-keywords-ai-driven-contextual-protection/ Thu, 27 Mar 2025 15:22:51 +0000 https://integralads.com/?p=340410 IAS didn’t improve keyword avoidance. We made it obsolete. Keyword-based brand safety is a relic. While others still rely on primitive keyword or URL scans, we’ve built a more sophisticated approach — one grounded in AI-powered, full-page contextual analysis. At...

The post Beyond Keywords: IAS’s AI-Driven Contextual Protection appeared first on Integral Ad Science.

]]>

IAS didn’t improve keyword avoidance. We made it obsolete.

Keyword-based brand safety is a relic. While others still rely on primitive keyword or URL scans, we’ve built a more sophisticated approach — one grounded in AI-powered, full-page contextual analysis. At IAS, keywords now account for just 0.25% of blocked or flagged impressions on buy-side open web traffic, based on IAS post-bid measurement from the past 30 days.

That’s not just low — it’s proof that AI-powered context is here to stay at IAS.

Keywords don’t get context. That’s the problem.

  • Overblocking: Keywords can’t understand nuance. “Shoot” could mean a camera or a crime scene. “Apple” could refer to a tech product or a healthy snack. Without context, you end up blocking premium, brand-safe inventory.
  • Underblocking: Keywords often miss real risks buried in the content. If it’s not in the URL string, it’s invisible to legacy systems.

IAS doesn’t just “check for words.” We deeply understand context.

Core capabilities powering IAS Context Control

Our AI-powered classification system analyzes full-page content, not just snippets or metadata, and processes approximately 15 billion unique URLs every 24 hours, using the following capabilities:

  • AI: IAS utilizes AI capabilities. Today, our natural language models interpret true meaning, sentiment, and intent — not just terms. We continue to invest to deliver even deeper content intelligence. 
  • Proprietary Knowledge Graph: Understands word relationships, industry nuance, and context across categories, tuned specifically for advertising.
  • Semantic Analysis: Distinguishes “Jaguar” the animal from the car brand in milliseconds.
  • 90+ Emotional & Sentiment Signals: Pinpoints tone — love, fear, outrage — to assess content suitability more precisely.
  • Entity Recognition: Detects people, places, and brands to match advertiser relevance.
  • 52+ Languages: Delivers global coverage with local nuance.

Built for precision. Powered by scale.

Not keywords. Not sampling. Full-page intelligence.

IAS doesn’t guess. We analyze every page at the moment of the first ad request — no shortcuts, no sampling, no extrapolation. Since launching Context Control in 2020, we’ve stuck to a simple principle: precision beats approximation.

That means better outcomes for advertisers and fairer representation for publishers, who benefit from fewer false blocks and more accurate classification of quality content.

Here’s how we deliver real contextual intelligence, at global scale:

  • Daily Score Refreshes: Every page we classify gets re-scored daily. That adds up to billions of refreshed context signals per week across the open web, ensuring your ad decisions reflect current content — not stale scans.
  • Dynamic Crawling: Pages that change more often (like news homepages) are crawled more frequently. Static pages? Less so. Our system adapts automatically.
  • Instant Decisioning: Advertising customers can choose to avoid unscored pages entirely. When a new page is encountered, it’s labeled “unscored” for just a few seconds before it’s fully classified and distributed across our systems and partners. No guessing. No delay.

Context Control is built for advertisers who want scale and control. We don’t cut corners. We classify everything.

Custom protection that fits your brand. At scale.

Advertisers don’t want black-box brand safety. They want clarity, control, and actionability. That’s why IAS built Context Control to deliver on the things marketers care about most: transparency and flexibility.

Here’s how we deliver:

  • Full Control with Infinite Flexibility
    Build your own brand suitability strategy with self-service tools that support everything from broad protection to hyper-specific needs. Choose from 280+ pre-built contextual segments — or create custom segments that reflect your brand’s unique risk tolerance, tone preferences, and industry nuances.
  • Granular Precision, Instantly Deployable
    Move beyond “high, medium, low” with fine-tuned subsets of industry-standard risk levels, enhanced by content-type modifiers (e.g., distinguishing between video game violence vs. breaking news coverage). Launch new protection strategies in minutes, not days — because media moves fast.
  • Transparent Classification You Can See and Act On
    Every customer gets URL-level reporting by default, so you know exactly which content is being flagged and why. No hidden logic or guesswork — just actionable visibility into the decisions our tech is making.

We go further with true URL detection, powered by our proprietary client-side script and fraud detection systems. That means we verify where an ad actually ran — not where it claims to. And when verification isn’t possible, IAS gives you proactive tools to avoid unclassified or invisible inventory altogether.

Contextual intelligence that goes beyond the open web

Context doesn’t stop at the article — and neither do we. IAS has expanded its contextual classification to social and video platforms, unlocking protection and performance across the content that dominates today’s media plans.

Our multimedia AI analyzes text, image, and audio at the frame level — delivering deep classification across social and video platforms like Meta, TikTok, and more. Whether it’s a trending video or a fast-moving social feed, IAS provides contextual understanding for multi-media.

Together, these capabilities provide advertisers with unified brand suitability definitions across both open web and walled gardens.

Innovating Further: Multi-Modal Models

IAS is pushing beyond today’s leading contextual capabilities with our patent-pending Multi-Modal Models, designed to analyze text, image, and video together, just like a human would. This unified, cross-format approach enables us to:

  • Understand content contextually, regardless of medium — enabling a far deeper and more nuanced understanding of context.
  • See how a brand is represented across all forms of media: which other brands it appears with, what types of content it’s featured in, and who’s talking about it.
  • Surface emerging concepts, even if they’ve never been predefined.
  • Build dynamic, on-demand contextual categories tailored to an advertiser’s needs.

IAS is creating a smarter, more adaptive way to understand and target digital content, pushing contextual classification into the next era of advertising.

We’ll dive deeper into our innovations in social and video classification in a future article, but know this: IAS is redefining suitability across every digital channel where ads run.

Protection meets performance

Brand safety shouldn’t come at the expense of scale — and with IAS, it doesn’t.

Our approach is data-driven, flexible, and built for results. By combining precise analysis with transparent control, we help advertisers protect their brand and hit their performance goals.

It’s not either-or. With IAS, it’s both.

The post Beyond Keywords: IAS’s AI-Driven Contextual Protection appeared first on Integral Ad Science.

]]>
IAS’s Approach to Brand Safety & Suitability https://integralads.com/insider/approach-to-brand-safety-suitability/ Mon, 24 Mar 2025 10:00:00 +0000 https://integralads.com/?p=340396 At IAS, we provide advertisers, media buyers, and publishers with robust tools and actionable insights to make educated, data-driven decisions. We believe transparency is essential for the digital ecosystem to thrive, driving efficiency and safety for all participants.

The post IAS’s Approach to Brand Safety & Suitability appeared first on Integral Ad Science.

]]>

Brand safety & suitability in a complex and ever-evolving digital ecosystem

Brand safety focuses on preventing ads from appearing next to content that is objectively harmful or inappropriate for a brand, such as hate speech, violence, or illegal activities.

Brand suitability, on the other hand, goes a step further, considering the nuanced context and alignment with a brand’s specific values and marketing goals. It helps ensure ads appear alongside content that not only avoids explicit harm but also resonates positively with the brand’s target audience and enhances conversion potential, leading to a contextually relevant and effective advertising experience.

At IAS, we provide advertisers, media buyers, and publishers with robust tools and actionable insights to make educated, data-driven decisions. We believe transparency is essential for the digital ecosystem to thrive, driving efficiency and safety for all participants.

The digital ad ecosystem is complex, and a multi-layered approach is necessary to mitigate risks, optimize media spend, and build confidence in digital investments. Our approach is designed to provide the most comprehensive, precise, and transparent solution for advertisers, assuring they have the right tools to protect their brand while maximizing reach — wherever they chose to spend their digital media dollars. 

It’s ultimately up to advertisers to define and implement their brand safety and suitability preferences, ensuring alignment with their unique brand values, risk tolerance, and campaign goals.

The goal of this article is to provide our customers, and the industry as a whole, a better understanding of our total solution for brand safety and suitability management, for the best possible outcome.

Best Practices for a Multi-Layered Brand Safety Strategy

Define Your Brand Risk Tolerance and Objectives: Use IAS Context Control over keywords to balance protection and scale, and make sure your media plan aligns with your settings. 

Leverage Pre-Bid and Post-Bid Controls: Pre-bid controls are integrated into media buying platforms (DSPs, social or video platforms) enabling buyers to bid on (or purchase) impressions that align to their unique needs. So why is it important to use pre-bid and post-bid controls together? One example benefit, within programmatic environments, is that the URL (or web page) reported in the bid request may not represent the actual web page originating the ad opportunity.

With IAS, post-bid controls offer an added layer of protection for buyers, since our post-bid tags are given the opportunity to find the true URL of a web page. This is in addition to the benefit of measuring multiple media quality metrics, such as viewability, IVT detection, geolocation and attention, in addition to brand safety. 

We recommend using IAS Context Control pre-bid segments to target safe and suitable content, while applying IAS post-bid blocking and verification to refine strategy and enforcement.

Understand Blocking and Monitoring Options: A helpful tool to balance both protection and scale is the use of tags that either block or measure events when they occur. At IAS, post-bid controls include the option to either block or measure the occurrence of brand safety or suitability concerns. Advertisers choose the approach based on a variety of factors, including targeting parameters or campaign performance goals.

It’s important to keep in mind that blocking can be limited by technical factors, such as a user’s preferences in a web browser or the acceptance by publishers.  

Use Quality Sync to Improve Governance and Operational Efficiency: Media buying operations often include multiple teams working together in separate locations around the globe to set up, display, and optimize dozens or even hundreds of advertising campaigns at any given time. Many CMOs and media departments want brand suitability standards implemented uniformly across all campaigns while maximizing team productivity.

IAS Quality Sync integrates with major DSPs to synchronize pre-bid brand safety and suitability settings with post-bid measurement and blocking to maximize media efficiencies, reduce operational workload, and support a uniform governance of standards across DSPs. Advertisers can simply set it once and apply it everywhere.

Make sure to share your IAS settings with the publishers for direct buys.

Promoting Scale While Protecting Brands: At IAS, we dissuade advertisers from relying on keyword exclusion tactics that scan for a single word (or words) on an entire webpage of content. Instead, our Context Control avoidance solution offers granular text analysis, reducing overblocking without relying on domain or keyword exclusion lists. We offer a vast number of configuration options, including both off-the-shelf and self-service, based on hundreds of content categories, emotion classification, and sentiment analysis.

Other tools, like domain and app exclusion and inclusion lists, are also available to meet advertiser objectives. 

  • Additional approaches:
    • Consider the source: Advertisers may decide to reduce or eliminate certain restrictions for some publishers. For example, a brand may decide that running next to content relating to “crime” on a news publisher is less of a concern, and the audience reach is a greater priority. Advertisers can easily accomplish this at the campaign-level within IAS Signal.  

Take Advantage of Transparency in Reporting: URL-level reporting is a great way to complement aggregated views of information. IAS provides URL-level reporting by default for every customer leveraging our Brand Suitability technology on the content that we label as unsafe or unsuitable. URL-level reporting is a self-service feature available within our custom report builder and summarizes the number of impressions labeled by each selected brand suitability segment or keyword, at the full URL level. 

In addition, we recommend leveraging IAS’s Total Visibility to understand where ads appear and optimize efficiency.  Total Visibility incorporates supply path data from major DSPs and SSPs, combined with advertiser-defined media quality metrics, to provide full visibility into the programmatic buying.  At the domain level, an ad buyer can see the full supply paths to purchase, along with metrics that quantify quality and value.

Continuously Optimize Brand Safety Settings: Regularly review URL-level and Total Visibility reports to continuously optimize your media buys. Review and adjust suitability thresholds and brand safety preferences using IAS Signal insights to meet the needs of your brand.

IAS provides full transparency, as well as consistent media quality metrics across environments to help you make the best decisions and have informed discussions with media partners.

Navigate Brand Safety and Suitability with Confidence

The digital ad ecosystem is complex and ever-evolving. That’s why a multi-layered approach to brand safety is key to confidently safeguard and scale your brand no matter where you’re spending your ad dollars. 

By leveraging a multi-layered strategy — which includes implementing pre-bid and post-bid controls, improving governance, and continually optimizing settings, among other tactics — advertisers can fine-tune their approach to align with their unique brand values and campaign goals. With IAS, advertisers have the tools and insights needed to navigate brand safety with confidence and drive superior results.

The post IAS’s Approach to Brand Safety & Suitability appeared first on Integral Ad Science.

]]>
IAS’s Multi-Tiered Approach to Combating Ad Fraud https://integralads.com/insider/iass-multi-tiered-approach-to-combating-ad-fraud/ Fri, 21 Mar 2025 17:46:54 +0000 https://integralads.com/?p=340382 Ad fraud is sophisticated and purpose-built to avoid detection. Bad actors attempt to identify new vulnerabilities, gaps, and attack vectors every day. The constant evolution of ad fraud requires a connected, multi-stage approach to detect and avoid. At IAS, we...

The post IAS’s Multi-Tiered Approach to Combating Ad Fraud appeared first on Integral Ad Science.

]]>

Ad fraud is sophisticated and purpose-built to avoid detection. Bad actors attempt to identify new vulnerabilities, gaps, and attack vectors every day. The constant evolution of ad fraud requires a connected, multi-stage approach to detect and avoid.

At IAS, we use a combined, AI-powered approach to detect ad fraud and protect our advertiser and publisher customers:

Pre-Bid

IAS advertisers are able to apply our fraud pre-bid avoidance segment to their campaigns within their DSPs. Our DSP partners decide whether or not to bid on a given bid request based on their engagement framework with IAS. Our DSP partners share information from the bid request such as URL, app bundle ID, and/or IP address. Based on our proprietary in-house fraud detection algorithms, we let the DSP know whether or not we would consider the impression to be invalid traffic or “IVT” (i.e., the impression is non-human).

Some of our DSP partners prefer not to share IP addresses. For these partners, we allow the DSP to check the IP address from the bid request against our list of known IVT IP addresses, and, if the IP address is on the list, advertisers can choose not to bid on the impression.

In either case, our pre-bid integrations benefit from the large scale of data we process post-bid and allow us to inform DSPs of bad IP addresses or sites.

Our DSP partners can leverage the IAB/ABC International Spiders & Bots List to detect and filter non-human traffic based on user agent pre-bid. IAS uses this information in post-bid processing.

Publishers can also prevent direct campaigns from displaying on fraudulent IPs by leveraging IAS’s Publisher Optimization product, which allows them to target ads away from impressions labeled as IVT.

Post-Bid (prior to ad render)

Our JavaScript tag is enabled prior to the ad rendering on the page. The tag inspects the page for URL, IP address, user agent, and many more signals not available pre-bid. We then assess if the impression is fraudulent or demonstrates any potential profile of ad fraud. If we determine the impression is fraudulent, we block the ad from rendering or report on the presence of IVT, depending on advertisers’ settings.

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. When publisher monitoring tags are in use, we label impressions as IVT where appropriate so publishers and advertisers can quantify IVT rates, but the creatives are still rendered. Publishers can use our previously mentioned Publisher Optimization service to target ads away from IPs labeled as IVT.

Post-Bid (post ad render)

We have developed sophisticated machine learning models that continuously learn across different environments of operation (e.g., open web, mobile, CTV). These models analyze hundreds of signals to detect ad fraud, thereby providing us proactive fraud detection and mitigation capabilities.

Our extensive machine learning modeling capabilities allow us to detect IVT by analyzing data and activity patterns over time to delineate human behavior vs. non-human behavior mimicking human behavior. Detecting IVT requires analyzing data over time to identify patterns of activity not associated with real people (e.g., devices running 24×7; devices generating excessive volumes of ad requests). Most data that our technology processes comes post-bid via macros and our Firewall, which processes signals from multiple HTTP headers.

In addition, our Threat Lab, a team of reconnaissance engineers, analyzes the data output by our models to identify emerging fraud schemes. The team researches schemes to determine how they are working and then collaborates with our platform partners to combat those schemes. The recent Vapor Threat scheme identified by our Threat Lab is a prime example of this collaboration, which resulted in the removal of more than a hundred malicious apps from the Google Play Store.

The Ad Fraud Detection Flywheel

Our AI-powered approach identifies fraudulent sites and apps by looking at a multitude of signals, including IP addresses, and this information is used to power our pre-bid avoidance technology. We detect fraud at three different stages.  Everything we do is connected in a continuous “flywheel” effect. This holistic approach allows us to deliver the industry’s most robust fraud detection and avoidance solution to our clients. We work collaboratively and closely with industry participants to reduce fraud and the proliferation of bad actors by applying our solutions across the 280 billion digital interactions we see daily, and continuously evaluate and innovate our offerings to respond to today’s rapidly changing fraud threats.

The post IAS’s Multi-Tiered Approach to Combating Ad Fraud appeared first on Integral Ad Science.

]]>