# US 2025/0159000 A1 · Malicious request detection

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

- Number: US 2025/0159000 A1
- Document ID: US20250159000A1
- Status: Published application
- Kind: A1
- Application number: 18/389,475
- Filed: 2023-11-14
- Published: 2025-05-15
- Earliest claimed: 2023-11-14
- Assignees: Human Security, Inc.
- Applicants: Human Security, Inc.
- Inventors: Marina GRECHUHIN; Moshe INGBER; Ori GOLD
- Web page: https://patentgrep.com/patent/US20250159000A1

## CPC

- H04L 63/1416: {Event detection, e.g. attack signature detection}
- G06N 20/00: Machine learning
- H04L 63/10: {for controlling access to devices or network resources}
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Systems, methods, apparatuses, and computer program products for analyzing malware traffic with direct malware detonation. The method may include, collecting page data of a website, and information of a user request. The method may also include generating an algorithm and a baseline of authorized activity with the collected page data and the information of the user request. In addition, the method may include establishing legitimacy of the user request based on the algorithm and the baseline. Further, the method may include controlling access to a web application based on the legitimacy of the user request.

## Claims

### Claim 1

A method, comprising:
collecting page data of a website, and information of a user request;
generating an algorithm and a baseline of authorized activity with the collected page data and the information of the user request;
establishing legitimacy of the user request based on the algorithm and the baseline; and
controlling access to a web application based on the legitimacy of the user request.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the page data comprises at least one of the following:
uniform resource locator parts comprising a scheme, a path, or a query string,
hypertext markup language input elements data comprising an identifier, a name, a type, or a label, or
hypertext markup language format element data comprising x, y, width, or height.

### Claim 3 (depends on 1)

The method according to claim 1, wherein the user request comprises at least one of the following:
a body,
metadata, or
a request structure and order of elements.

### Claim 4 (depends on 1)

The method according to claim 1, further comprising:
feeding the algorithm and the baseline into a machine learning model; and
dynamically training the machine learning model based on the collected page data of the website.

### Claim 5 (depends on 4)

The method according to claim 4, further comprising:
determining, via the machine learning model, a web page type based on the collected page data.

### Claim 6 (depends on 1)

The method according to claim 1, wherein controlling access comprises:
granting access to the web application when the user request is established as legitimate; and
denying access to the web application when the request is established as illegitimate.

### Claim 7 (depends on 6)

The method according to claim 6,
wherein the user request is established as legitimate when the baseline and the information of the user request correspond with each other, and
wherein the user request is established as illegitimate when the baseline and the information of the user request do not correspond with each other.

### Claim 8

An apparatus, comprising:
at least one processor; and
at least one memory comprising computer program code,
the at least one memory and the computer program code configured to, when executed by the at least one processor, cause the apparatus at least to:
collect page data of a website, and information of a user request;
generate an algorithm and a baseline of authorized activity with the collected page data and the information of the user request;
establish legitimacy of the user request based on the algorithm and the baseline; and
control access to a web application based on the legitimacy of the user request.

### Claim 9 (depends on 8)

The apparatus according to claim 8, wherein the page data comprises at least one of the following:
uniform resource locator parts comprising a scheme, a path, or a query string,
hypertext markup language input elements data comprising an identifier, a name, a type, or a label, or
hypertext markup language format element data comprising x, y, width, or height.

### Claim 10 (depends on 8)

The apparatus according to claim 8, wherein the user request comprises at least one of the following:
a body,
metadata, or
a request structure and order of elements.

### Claim 11 (depends on 8)

The apparatus according to claim 8, wherein the at least one memory and the computer program code are further configured to, when executed by the at least one processor, cause the apparatus at least to:
feed the algorithm and the baseline into a machine learning model; and
dynamically train the machine learning model based on the collected page data of the website.

### Claim 12 (depends on 8)

The apparatus according to claim 8, wherein the at least one memory and the computer program code are further configured to, when executed by the at least one processor, cause the apparatus at least to:
determine, via the machine learning model, a web page type based on the collected page data.

### Claim 13 (depends on 8)

The apparatus according to claim 8, wherein controlling access comprises:
granting access to the web application when the user request is established as legitimate; and
denying access to the web application when the request is established as illegitimate.

### Claim 14 (depends on 13)

The apparatus according to claim 13,
wherein the user request is established as legitimate when the baseline and the information of the user request correspond with each other, and
wherein the user request is established as illegitimate when the baseline and the information of the user request do not correspond with each other.

### Claim 15

A computer program, embodied on a non-transitory computer readable medium, the computer program comprising computer executable code, which, when executed by a processor, causes the processor to:
collect page data of a website, and information of a user request;
generate an algorithm and a baseline of authorized activity with the collected page data and the information of the user request;
establish legitimacy of the user request based on the algorithm and the baseline; and
control access to a web application based on the legitimacy of the user request.

### Claim 16 (depends on 15)

The computer program according to claim 15, wherein the page data comprises at least one of the following:
uniform resource locator parts comprising a scheme, a path, or a query string,
hypertext markup language input elements data comprising an identifier, a name, a type, or a label, or
hypertext markup language format element data comprising x, y, width, or height.

### Claim 17 (depends on 15)

The computer program according to claim 15, wherein the user request comprises at least one of the following:
a body,
metadata, or
a request structure and order of elements.

### Claim 18 (depends on 15)

The computer program according to claim 15, wherein the processor is further caused to:
feed the algorithm and the baseline into a machine learning model; and
dynamically train the machine learning model based on the collected page data of the website.

### Claim 19 (depends on 18)

The computer program according to claim 18, wherein the processor is further caused to:
determine, via the machine learning model, a web page type based on the collected page data.

### Claim 20 (depends on 15)

The computer program according to claim 15, wherein controlling access comprises:
granting access to the web application when the user request is established as legitimate; and
denying access to the web application when the request is established as illegitimate.
