Granted Patent B2

US 12,536,562 · App. 18/244,502 · Granted Jan 27, 2026

Inventors: Jason Lloyd Shaw (New York, NY); David William Luttrell (Philadelphia, PA); Arun Ahuja (Stamford, CT)

Assignee: Integral Ad Science, Inc.

G06Q30/0248

Abstract

Claims (51)

1 . A method for detecting suspicious activity from a plurality of websites, the method comprising:

receiving, using a server that includes a hardware processor, advertisement impression information associated with a plurality of pages;

determining, by the server, from the received advertisement impression information, a viewability statistic for each of the plurality of pages, wherein the viewability statistic indicates a likelihood of whether an advertisement displayed on a webpage was never within a viewable area in a browser window rendered by a browser application;

determining, by the server, a viewability score for the advertisement impression based on the viewability statistic;

identifying, by the server, the advertisement impression as likely being suspicious based on the determined viewability score; and

intercepting, by the server, an advertisement call associated with a page on which the advertisement impression identified as likely being suspicious, wherein the advertisement call is modified with information relating to the advertisement impression identified as likely being suspicious that inhibits an advertiser from placing a bid to place one or more content items in a content inventory associated with the advertiser in a corresponding advertisement placement.

2 . The method of claim 1 , further comprising inhibiting content associated with the advertisement impression identified as likely to be suspicious from being purchased for advertisement placement.

3 . The method of claim 1 , further comprising transmitting information relating to the identified advertisement impression that inhibits the advertiser from associating with a corresponding website.

4 . The method of claim 1 , wherein the viewability statistic comprises a fraction of advertisement impressions that was never in the viewable area of the browser window.

5 . The method of claim 1 , further comprising identifying at least one website as likely to be suspicious based on the viewability score by determining that the viewability statistic exceeds a selected threshold value, wherein the selected threshold value indicates that the at least one website is engaging in suspicious activity.

6 . The method of claim 1 , further comprising:

determining a portion of the plurality of pages corresponding to the website;

determining one or more advertisements presented on the portion of the plurality of pages; and

determining a plurality of browsers associated with advertisement calls for the one or more advertisements.

7 . The method of claim 1 , further comprising:

extracting identification data associated with at least one website that is deemed suspicious;

searching for other websites having identification data that is similar to the extracted identification data; and

determining whether at least one of the other websites should be deemed as likely to be suspicious.

8 . The method of claim 1 , further comprising:

receiving training data;

identifying features for differentiating suspicious websites from normal websites using the received training data; and

using a classifier with the identified features to identify the suspicious websites from the plurality of websites.

9 . A system for detecting suspicious activity from a plurality of websites, the system comprising:

a server that includes a hardware processor that:

receives advertisement impression information associated with a plurality of pages;

determines, from the received advertisement impression information, a viewability statistic for each of the plurality of pages, wherein the viewability statistic indicates a likelihood of whether an advertisement displayed on a webpage was never within a viewable area in a browser window rendered by a browser application;

determines a viewability score for the advertisement impression based on the viewability statistic;

identifies the advertisement impression as likely being suspicious based on the determined viewability score; and

intercepts an advertisement call associated with a page on which the advertisement impression identified as likely being suspicious, wherein the advertisement call is modified with information relating to the advertisement impression identified as likely being suspicious that inhibits an advertiser from placing a bid to place one or more content items in a content inventory associated with the advertiser in a corresponding advertisement placement.

10 . The system of claim 9 , wherein the hardware processor further inhibits content associated with the advertisement impression identified as likely to be suspicious from being purchased for advertisement placement.

11 . The system of claim 9 , wherein the hardware processor further transmits information relating to the identified advertisement impression that inhibits the advertiser from associating with a corresponding website.

12 . The system of claim 9 , wherein the viewability statistic comprises a fraction of advertisement impressions that was never in the viewable area of the browser window.

13 . The system of claim 9 , wherein the hardware processor further identifies at least one website as likely to be suspicious based on the viewability score by determining that the viewability statistic exceeds a selected threshold value, wherein the selected threshold value indicates that the at least one website is engaging in suspicious activity.

14 . The system of claim 9 , wherein the hardware processor further:

determines a portion of the plurality of pages corresponding to the website;

determines one or more advertisements presented on the portion of the plurality of pages; and

determines a plurality of browsers associated with advertisement calls for the one or more advertisements.

15 . The system of claim 9 , wherein the hardware processor further:

extracts identification data associated with at least one website that is deemed suspicious;

searches for other websites having identification data that is similar to the extracted identification data; and

determines whether at least one of the other websites should be deemed as likely to be suspicious.

16 . The system of claim 9 , wherein the hardware processor further:

receives training data;

identifies features for differentiating suspicious websites from normal websites using the received training data; and

uses a classifier with the identified features to identify the suspicious websites from the plurality of websites.

17 . A non-transitory computer-readable medium containing computer-executable instructions that, when executed by a processor, cause the processor to perform a method for detecting suspicious activity from a plurality of websites, the method comprising:

receiving advertisement impression information associated with a plurality of pages;

determining, from the received advertisement impression information, a viewability statistic for each of the plurality of pages, wherein the viewability statistic indicates a likelihood of whether an advertisement displayed on a webpage was never within a viewable area in a browser window rendered by a browser application;

determining a viewability score for the advertisement impression based on the viewability statistic;

identifying the advertisement impression as likely being suspicious based on the determined viewability score; and

intercepting an advertisement call associated with a page on which the advertisement impression identified as likely being suspicious, wherein the advertisement call is modified with information relating to the advertisement impression identified as likely being suspicious that inhibits an advertiser from placing a bid to place one or more content items in a content inventory associated with the advertiser in a corresponding advertisement placement.

Assignments (3)

Continuity (5)

References Cited (57)