Crowdsourced Ad Blocking via Image and URL Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing ad-blocking tools indiscriminately block all advertisements, including both deceptive and legitimate ones, which is unsustainable for content providers relying on advertising revenue, and fail to effectively differentiate between the two, leading to phishing attacks and scams.
Innovation Solution
A method utilizing crowdsourced ad blocking data and browser extensions that analyze image and URL data to generate a list of blocked ads, preventing only deceptive ads from being rendered, while allowing legitimate ads to remain visible and generating revenue for content providers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If existing ad-blocking tools block all advertisements in a content-neutral manner, then users are protected from deceptive ads, but legitimate ads are also blocked causing loss of advertising revenue for content providers
Solution Approach 1:
The patent applies local quality by differentiating between deceptive and legitimate ads based on their specific characteristics. Instead of uniform blocking, the system analyzes ad content, metadata, and behavior patterns to identify harmful properties specific to deceptive ads while preserving legitimate advertising content.
Solution Approach 2:
The system extracts harmful characteristics from ads by analyzing specific properties such as redirect behavior, content patterns, and metadata anomalies. By isolating these harmful traits, the system can target only deceptive ads for blocking while allowing legitimate ads to pass through.
2Ease of manufacture
If existing ad-blocking tools use network address or domain-based blocking, then implementation is simple, but the system lacks precision in identifying deceptive versus legitimate ads
Solution Approach 1:
The patent segments ad analysis into multiple independent components: content analysis, metadata examination, behavior pattern detection, and reputation assessment. Each component processes specific aspects of ad data, and the results are combined to make precise classification decisions.
Solution Approach 2:
The system introduces an intermediary analysis layer that sits between ad delivery and user interaction. This intermediary component evaluates ad characteristics and makes intelligent decisions about blocking, providing precise classification without requiring complex user-side processing.
3Loss of energy
If website operators employ techniques to detect ad-blockers and prevent user access, then advertising revenue is protected, but user experience deteriorates and legitimate ad blocking capabilities are compromised
Solution Approach 1:
The system implements feedback mechanisms where ad performance data, user behavior patterns, and blocking effectiveness are continuously monitored and fed back into the analysis system. This feedback loop enables continuous improvement of ad classification accuracy, allowing better differentiation between deceptive and legitimate ads.
Data Source
AI summary
In one aspect, the present disclosure relates to a method for reducing fraud in computer networks, the method including receiving, from each of a plurality of user devices, a request to block an ad displayed within a web browser installed on the user device, the request comprising image data and a forwarding URL associated with the ad; storing crowdsourced ad blocking data based on the received requests to block ads; receiving a request for a list of blocked ads; generating a list of blocked ads based on analyzing the crowdsourced ad blocking data, wherein analyzing the crowdsourced ad blocking data comprises identifying ads blocked by at least a threshold number of users; and sending the list of blocked ads to a first user device, the first user device comprising a browser extension configured to prevent ads within the list of blocked ads from being rendered in a browser.