# US 2010/0169971 A1 · Methods for user profiling for detecting insider threats based on internet search patterns and forensics of search keywords

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

- Number: US 2010/0169971 A1
- Document ID: US20100169971A1
- Status: Published application
- Kind: A1
- Application number: 12/344,229
- Filed: 2008-12-25
- Published: 2010-07-01
- Earliest claimed: 2008-12-25
- Assignees: Check Point Software Technologies Ltd.
- Inventors: Gil RAVIV
- Web page: https://patentgrep.com/patent/US20100169971A1

## CPC

- H04L 63/1408: {by monitoring network traffic (monitoring network traffic per se H04L43/00)}
- G06F 21/316: {by observing the pattern of computer usage, e.g. typical user behaviour}
- G06F 21/552: {involving long-term monitoring or reporting}
- 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

Disclosed are methods for user profiling for detecting insider threats including the steps of: upon a client application sending a request for a link, extracting at least one search keyword from a search session associated with the request; classifying the link into at least one classification; determining whether at least one classification is a monitored classification; capturing search elements of search sessions associated with the monitored classification; acquiring usage data from the search elements to create a user profile associated with a user's search behavior; and performing a statistical analysis, on a search frequency for the monitored classification, on user profiles associated with many users. Preferably, the method includes: designating a profile as suspicious based on the statistical analysis exceeding a pre-determined threshold value, wherein the pre-determined threshold value is based on an expected search frequency for the profile and each respective grade for at least one risk-assessment dimension.

## Claims

### Claim 1

A method for user profiling for detecting insider threats, the method comprising the steps of:
(a) upon a client application sending a request for a URI (Uniform Resource Identifier) web link, extracting at least one search keyword from a search session associated with said request;
(b) classifying said URI web link into at least one classification;
(c) determining whether said at least one classification is a monitored classification;
(d) capturing search elements of search sessions associated with said monitored classification;
(e) acquiring usage data from said search elements to create a user profile associated with a user's search behavior; and
(f) performing a statistical analysis, on a search frequency for said monitored classification, on user profiles associated with many users.

### Claim 2 (depends on 1)

The method of claim 1, wherein said step of classifying includes categorizing said URI web link into at least one category, and wherein said at least one category is included in said at least one classification.

### Claim 3 (depends on 1)

The method of claim 1, wherein said step of performing said statistical analysis yields a respective grade in at least one risk-assessment dimension selected from the group consisting of: knowledge/skill, intent, accessibility, and reputation.

### Claim 4 (depends on 3)

The method of claim 3, the method further comprising the step of:
(g) designating a user profile as suspicious based on said statistical analysis exceeding a pre-determined threshold value, wherein said pre-determined threshold value is based on an expected search frequency for said user profile and each said respective grade for said at least one risk-assessment dimension.

### Claim 5 (depends on 4)

The method of claim 4, the method further comprising the step of:
(h) segmenting said statistical analysis according to an organizational department associated with said user profile.

### Claim 6 (depends on 5)

The method of claim 5, wherein said expected search frequency is dependent on said organizational department.

### Claim 7 (depends on 1)

The method of claim 1, wherein said step of acquiring is performed periodically in order to provide a time-dependent component to said user profile.

### Claim 8 (depends on 7)

The method of claim 7, wherein said time-dependent component is used to modify an expected search frequency.

### Claim 9 (depends on 8)

The method of claim 8, wherein said step of performing said statistical analysis yields a respective grade in at least one risk-assessment dimension selected from the group consisting of: knowledge/skill, intent, accessibility, and reputation.

### Claim 10 (depends on 9)

The method of claim 9, the method further comprising the step of:
(g) designating a user profile as suspicious based on said statistical analysis exceeding a pre-determined threshold value, wherein said pre-determined threshold value is based on said expected search frequency for said user profile and each said respective grade for said at least one risk-assessment dimension.

### Claim 11

A computer-readable storage medium having computer-readable code embodied on the computer-readable storage medium, the computer-readable code comprising:
(a) program code for, upon a client application sending a request for a URI (Uniform Resource Identifier) web link, extracting at least one search keyword from a search session associated with said request;
(b) program code for classifying said URI web link into at least one classification;
(c) program code for determining whether said at least one classification is a monitored classification;
(d) program code for capturing search elements of search sessions associated with said monitored classification;
(e) program code for acquiring usage data from said search elements to create a user profile associated with a user's search behavior; and
(f) program code for performing a statistical analysis, on a search frequency for said monitored classification, on user profiles associated with many users.

### Claim 12 (depends on 11)

The storage medium of claim 11, wherein said program code for classifying includes program code for categorizing said URI web link into at least one category, and wherein said at least one category is included in said at least one classification.

### Claim 13 (depends on 11)

The storage medium of claim 11, wherein said program code for performing said statistical analysis is operative to yield a respective grade in at least one risk-assessment dimension selected from the group consisting of: knowledge/skill, intent, accessibility, and reputation.

### Claim 14 (depends on 13)

The storage medium of claim 13, the computer-readable code further comprising:
(g) program code for designating a user profile as suspicious based on said statistical analysis exceeding a pre-determined threshold value, wherein said pre-determined threshold value is based on an expected search frequency for said user profile and each said respective grade for said at least one risk-assessment dimension.

### Claim 15 (depends on 14)

The storage medium of claim 14, the computer-readable code further comprising:
(h) program code for segmenting said statistical analysis according to an organizational department associated with said user profile.

### Claim 16 (depends on 15)

The storage medium of claim 15, wherein said expected search frequency is dependent on said organizational department.

### Claim 17 (depends on 11)

The storage medium of claim 11, wherein said program code for acquiring is operative to be performed periodically in order to provide a time-dependent component to said user profile.

### Claim 18 (depends on 17)

The storage medium of claim 17, wherein said time-dependent component is used to modify an expected search frequency.

### Claim 19 (depends on 18)

The storage medium of claim 18, wherein said program code for performing said statistical analysis is operative to yield a respective grade in at least one risk-assessment dimension selected from the group consisting of: knowledge/skill, intent, accessibility, and reputation.

### Claim 20 (depends on 19)

The storage medium of claim 19, the computer-readable code further comprising:
(g) program code for designating a user profile as suspicious based on said statistical analysis exceeding a pre-determined threshold value, wherein said pre-determined threshold value is based on said expected search frequency for said user profile and each said respective grade for said at least one risk-assessment dimension.
