Phishing Detection via Image Hashing and Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current information security technologies lack a reliable and efficient solution for detecting and identifying phishing websites.

Innovation Solution

The system uses image hashing to generate overall hash values for websites, comparing these values to identify phishing websites by correlating images between known phishing sites and suspect websites.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If image hashing is used to detect phishing websites, then detection reliability is improved, but computational complexity increases

Engineering Contradiction:
Improvephishing website detection reliabilityVSAvoidcomputational complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the website detection process into multiple independent hash computations, one for each image on the website. Instead of analyzing the entire website as a single unit, the system divides it into discrete image elements, computes individual hash values for each, and then aggregates these hashes. This segmentation approach maintains high detection reliability while reducing computational complexity by enabling parallel processing and incremental hash updates when images change.

Inventive Principle:
Principle #1Segmentation

2Measurement precision

If multiple images are extracted and hashed from each website, then detection precision is improved, but processing time increases

Engineering Contradiction:
Improvephishing website identification precisionVSAvoidwebsite processing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies preliminary action by pre-computing and storing hash values for images from known legitimate websites before phishing detection is needed. When a website is evaluated for phishing, the system retrieves these pre-computed hashes and compares them against the hashes of images on the evaluated website. This eliminates the need to re-hash images during the actual detection process, significantly reducing processing time while maintaining high identification precision through accurate hash matching.

Inventive Principle:
Principle #10Preliminary action

3Ease of operation

If the system compares overall hash values to identify phishing websites, then ease of operation is improved, but detection coverage decreases

Engineering Contradiction:
Improvephishing website identification easeVSAvoiddetection coverage
Core Design Contradiction:
Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent implements partial action by comparing only specific image hashes rather than requiring complete website hash matching. The system identifies phishing websites by finding sufficient matches between image hashes on the evaluated website and those in the database of known websites. This partial matching approach simplifies operation while maintaining broad detection coverage, as it can identify phishing sites even when not all images are identical or when images have been slightly modified.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS12341813B2Information security system and method for phishing website identification based on image hashing
Publication Date: 2025.06.24 BANK OF AMERICA CORP
  • US12341813B2 patent drawing
  • US12341813B2 patent drawing
  • US12341813B2 patent drawing

AI summary

A system for detecting phishing websites accesses a website that comprises a plurality of images. The system extracts the plurality of images from the website. The system generates a hash value for each image from the plurality of images. Each hash value uniquely identifies its corresponding image. The system generates a first overall hash value for the website by hashing the generated hash values. The first overall hash value represents a signature of the website. The system compares the first overall hash value with a second overall hash value that is associated with a phishing website. The system determines whether the first overall hash value corresponds to the second overall hash value. If it is determined that the first overall hash value corresponds to the second overall hash value, the system determines that the website is associated with the phishing website.