Homepage Forgery Detection via OCR and Static Area Masking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for detecting homepage forgery/falsification via website hacking often result in false positives due to normal dynamic variations, and fail to accurately detect partial falsifications, which are difficult to automate.
Innovation Solution
An apparatus and method utilizing Optical Character Recognition (OCR) to extract and compare character strings from homepage image shots, with a learning module to classify strings as normal or falsified, and manage reference databases for precise detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional source code comparison methods are used to detect homepage forgery, then detection coverage is provided, but false positive alarms increase due to normal dynamic variations
Solution Approach 1:
The patent extracts only the static area information from the homepage image using masking technology, separating it from the dynamic area. By focusing analysis only on the static area character strings, the system eliminates false positives caused by normal updates in the dynamic area while maintaining detection capability for actual forgeries.
Solution Approach 2:
The patent creates a masked image that copies only the static area of the homepage, effectively isolating the region of interest. This copied static area is then used for comparison with historical data, enabling accurate forgery detection without being misled by normal dynamic changes.
2Reliability
If masking technique is used to analyze static and dynamic areas, then static area forgery detection is improved, but partial falsification of dynamic area becomes undetectable
Solution Approach 1:
The patent segments the homepage into static and dynamic areas using masking, then further segments the static area into multiple character string regions. This segmentation allows the system to detect forgeries in specific static regions even when the overall dynamic area contains normal variations or partial forgeries.
Solution Approach 2:
The patent applies different analysis qualities to different regions: the static area receives detailed character string comparison analysis, while the dynamic area is handled through masking exclusion. This local differentiation enables detection of partial forgeries in the static area without being confused by normal dynamic updates.
3Measurement precision
If character string extraction and comparison methods are used, then detection precision is improved, but system complexity increases
Solution Approach 1:
The patent replaces complex source code parsing and comparison mechanisms with image processing and optical character recognition (OCR). By converting the homepage to an image and extracting character strings visually, the system simplifies the detection mechanism while improving precision in identifying static area forgeries.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach allows for prompt and precise identification of homepage forgery/falsification, improving detection accuracy and reducing false positives, including detection of partial area falsifications.
Implementation Method 1
a character string extraction module for extracting character strings from each homepage image shot using an Optical Character Recognition (OCR) technique
Data Source
AI summary
An apparatus and method for detecting forgery/falsification of a homepage. The apparatus includes a homepage image shot generation module for generating homepage image shots of an entire screen of an accessed homepage. A character string extraction module extracts character strings from each homepage image shot using an OCR technique. A character string comparison module compares each of the extracted character strings with character strings required for determination of homepage forgery/falsification, thus determining whether the extracted character string is a normal character string or a falsified character string. A homepage falsification determination module determines whether the corresponding homepage has been forged/falsified, based on results of the comparison. A character string learning module learns the character string extracted from the homepage image shot, based on results of the determination, and classifies the character string as the normal character string or the falsified character string.