Identifying and blocking fraudulent websites
AssigneeMassachusetts Mutual Life Insurance Company
InventorsDamon Ryan Depaolo, Payton A. Shubrick
Life of this patent
Estimating the term…
Abstract
A system may generate all possible character mistakes in a first uniform resource locator associated with a first website, which may produce a set of unique and similar uniform resource locators associated with a set of similar websites. The system may execute machine vision algorithms to compare visual images of the first website and the set of similar websites, and identify a subset of similar websites, which may be undistinguishable from the first website. The system may block the subset of websites, and thereby prevent any user from accessing these fraudulent and malicious websites.
Claims18
A server-implemented method comprising:
- receiving, by a server from an administrator computer, a first uniform resource locator corresponding to a first website having first visual attributes;
- executing, by the server, a permutation protocol to generate a set of similar uniform resource locators based on the first uniform resource locator;
- crawling, by the server, a set of websites where each website corresponds to each similar uniform resource locator of the set of similar uniform resource locators, wherein the server executes a screen scraping protocol to identify visual attributes associated with each of the set of websites;
- comparing, by the server, each visual attribute with the first visual attributes to identify a subset of websites from the set of websites such that each website within the subset of websites comprises the visual attributes that satisfy a similarity threshold with respect to the first visual attributes, wherein the visual attributes of each website comprises one or more of a shape of each item, a size of each item, a font of each item, a color of each item, or a position of each item on a webpage of each website;
- comparing transmitting, by the server to a webserver, an instruction to block each website within the subset of websites;
- and generating, by the server, a watch list comprising remaining websites of the set of websites, wherein the server periodically monitors content in each website within the watch list.
A system comprising:
- a server configured to:
- receive from an administrator computer, a first uniform resource locator corresponding to a first website having first visual attributes;
- execute a permutation protocol to generate a set of similar uniform resource locators based on the first uniform resource locator;
- crawl a set of websites where each website corresponds to each similar uniform resource locator of the set of similar uniform resource locators, wherein the server executes a screen scraping protocol to identify visual attributes associated with each of the set of websites;
- compare, by the server, each visual attribute with the first visual attributes to identify a subset of websites from the set of websites such that each website within the subset of websites comprises the visual attributes that satisfy a similarity threshold with respect to the first visual attributes, wherein the visual attributes of each website comprises one or more of a shape of each item, a size of each item, a font of each item, a color of each item, or a position of each item on a webpage of each website;
- transmit to a webserver, an instruction to block each website within the subset of websites;
- and generate a watch list comprising remaining websites of the set of websites, wherein the server periodically monitors content in each website within the watch list.
Dependencies are inferred from the claim text.