# US 2019/0173894 A1 · Systems and methods for phishing and brand protection

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2019/0173894 A1
- Document ID: US20190173894A1
- Status: Published application
- Kind: A1
- Application number: 16/266,984
- Filed: 2019-02-04
- Published: 2019-06-06
- Earliest claimed: 2015-08-05
- Assignees: McAfee, Inc.
- Applicants: McAfee, LLC
- Inventors: SIMON HUNT; VENKATA RAMANAN SAMBANDAM
- Web page: https://patentgrep.com/patent/US20190173894A1

## CPC

- H04L 63/1416: {Event detection, e.g. attack signature detection}
- G06F 21/645: {using a third party}
- G06F 2221/2119: Authenticating web pages, e.g. with suspicious links
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Systems and methods for phishing and brand protection of websites via copycat detection are disclosed herein. An example apparatus includes at least one processor, a display, and memory including instructions that, when executed, cause the at least one processor to determine a first hash of a first image in a webpage and a second hash of a second image in the webpage, the second image different from the first image, the first hash different from the second hash, generate a temporary page profile associated with the webpage based on the first hash and the second hash, fuzzy match the temporary page profile to a baseline page profile, and in response to a determination that the temporary page profile does not match the baseline page profile, generate an alert to be displayed via the display to indicate that fraud has been detected for the webpage.

## Claims

### Claim 1

An apparatus to detect fraud in a webpage, the apparatus comprising:
at least one processor;
a display;
memory including instructions that, when executed, cause the at least one processor to:
determine a first hash of a first image in a webpage and a second hash of a second image in the webpage, the second image different from the first image, the first hash different from the second hash;
generate a temporary page profile associated with the webpage based on the first hash and the second hash;
fuzzy match the temporary page profile to a baseline page profile; and
in response to a determination that the temporary page profile does not match the baseline page profile, generate an alert to be displayed via the display to indicate that fraud has been detected for the webpage.

### Claim 2 (depends on 1)

The apparatus of claim 1, wherein the at least one processor is to add the webpage to a white list in response to an input from the user.

### Claim 3 (depends on 1)

The apparatus of claim 1, wherein the at least one processor is to generate the temporary page profile associated with the webpage in response to a trigger event indicating potential fraud associated with the webpage.

### Claim 4 (depends on 1)

The apparatus of claim 1, wherein the at least one processor is to store the temporary page profile as one of the baseline page profiles.

### Claim 5 (depends on 1)

The apparatus of claim 1, wherein the at least one processor is to initiate transmission of a report to a remote location, the report indicating that the webpage is fraudulent, the report to include the temporary page profile and the baseline page profile.

### Claim 6 (depends on 1)

The apparatus of claim 1, wherein the at least one processor is to fuzzy match the temporary page profile to the baseline page profile based on a MinHash matching algorithm.

### Claim 7 (depends on 1)

The apparatus of claim 1, wherein the at least one processor is to retrieve the baseline page profile from the memory.

### Claim 8

A storage disk or storage device comprising computer-executable instructions which, when executed by a processor, cause the processor to at least:
determine a first hash of a first image in a webpage and a second hash of a second image in the webpage, the second image different from the first image, the first hash different from the second hash;
generate a temporary page profile associated with the webpage based on the first hash and the second hash;
fuzzy match the temporary page profile to a baseline page profile; and
in response to a determination that the temporary page profile does not match the baseline page profile, generate an alert to indicate that fraud has been detected for the webpage.

### Claim 9 (depends on 8)

The storage disk or storage device of claim 8, wherein the instructions, when executed, cause the processor to add the webpage to a white list in response to an input from a user.

### Claim 10 (depends on 8)

The storage disk or storage device of claim 8, wherein the instructions cause the processor to generate the temporary page profile associated with the webpage in response to a trigger event corresponding to potential fraud associated with the webpage.

### Claim 11 (depends on 8)

The storage disk or storage device of claim 8, wherein the instructions cause the processor to initiate storage of the temporary page profile as one of the baseline page profiles.

### Claim 12 (depends on 8)

The storage disk or storage device of claim 8, wherein the instructions cause the processor to initiate transmission of a report to a remote location, the report to indicate that the webpage is fraudulent, the report to include the temporary page profile and the baseline page profile.

### Claim 13 (depends on 8)

The storage disk or storage device of claim 8, wherein the instructions cause the processor to fuzzy match the temporary page profile to the baseline page profile based on a MinHash matching algorithm.

### Claim 14 (depends on 8)

The storage disk or storage device of claim 8, wherein the instructions cause the processor to initiate retrieval of the baseline page profile from a local memory.

### Claim 15

A method to detect fraud in a webpage, the method comprising:
determine, by executing an instruction with a processor, a first hash of a first image in a webpage and a second hash of a second image in the webpage, the second image different from the first image, the first hash different from the second hash;
generating a temporary page profile associated with the webpage based on the first hash and the second hash;
fuzzy matching the temporary page profile to a baseline page profile; and
in response to a determination that the temporary page profile does not match the baseline page profile, generating an alert to indicate that fraud has been detected for the webpage.

### Claim 16 (depends on 15)

The method of claim 15, further including adding the webpage to a white list in response to an input from a user.

### Claim 17 (depends on 15)

The method of claim 15, further including generating the temporary page profile associated with the webpage in response to a trigger event corresponding to potential fraud associated with the webpage.

### Claim 18 (depends on 15)

The method of claim 15, further including initiating storage of the temporary page profile as one of the baseline page profiles.

### Claim 19 (depends on 15)

The method of claim 15, further including transmitting a report to a remote location, the report to indicate that the webpage is fraudulent, the report to include the temporary page profile and the baseline page profile.

### Claim 20 (depends on 15)

The method of claim 15, wherein the fuzzy matching of the temporary page profile to the baseline page profile includes based on a MinHash matching algorithm.
