# US 2015/0150104 A1 · Dynamic security question generation

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

- Number: US 2015/0150104 A1
- Document ID: US20150150104A1
- Status: Published application
- Kind: A1
- Application number: 14/457,148
- Filed: 2014-08-12
- Published: 2015-05-28
- Earliest claimed: 2013-11-25
- Inventors: Roy S. Melzer
- Web page: https://patentgrep.com/patent/US20150150104A1

## CPC

- G06F 21/45: Structures or tools for the administration of authentication
- G06F 21/316: {by observing the pattern of computer usage, e.g. typical user behaviour}
- G06N 20/00: Machine learning
- H04L 63/08: {for authentication of entities (cryptographic mechanisms or cryptographic arrangements for entity authentication H04L9/32)}
- G06F 2221/2101: Auditing as a secondary aspect
- G06F 2221/2111: Location-sensitive, e.g. geographical location, GPS
- H04L 63/107: {wherein the security policies are location-dependent, e.g. entities privileges depend on current location or allowing specific operations only from locally connected terminals}
- H04L 63/1425: {Traffic logging, e.g. anomaly detection}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

A method of dynamically generating a security question for accessing a resource. The method comprises monitoring a behavior of said user during a monitoring period to identify automatically a deviation from a behavioral pattern indicative of repetitive behavior of a user, automatically generating a security question responded to by an indication of said deviation, receiving a user input inputted by a user in response to a presentation of said security question and said deviation, and authenticating, after said monitoring period, an access to a resource according to a match between said user input and said deviation.

## Claims

### Claim 1

A method of dynamically generating a security question for accessing a resource, comprising:
monitoring a behavior of a user during a monitoring period to identify automatically a deviation from a behavioral pattern indicative of repetitive behavior of said user;
automatically generating a security question responded to by an indication of said deviation;
receiving a user input in response to a presentation of said security question; and
authenticating an access to a resource according to a match between said user input and said deviation.

### Claim 2 (depends on 1)

The method of claim 1, wherein said monitoring comprises recoding said behavior during a pre monitoring period of at least one day and calculating said behavioral pattern from a classification of said behavior during said pre monitoring period.

### Claim 3 (depends on 2)

The method of claim 2, wherein said recorded behavior is used as a training set for creating a classifier, said deviation is identified using said classifier.

### Claim 4 (depends on 1)

The method of claim 1, further comprising associating between said resource and said security question after said monitoring period; wherein said authenticating comprises selecting said security question according to said association.

### Claim 5 (depends on 1)

The method of claim 1, wherein said behavioral pattern is calculated by gathering locational data logging at least one of a route, a location and a movement of the user during a pre-monitoring period that precedes said monitoring period, said deviation is a deviation from at least one of said route, said location and said movement at a respective time at a respective time during said monitoring period.

### Claim 6 (depends on 1)

The method of claim 1, wherein said behavioral pattern is calculated by gathering browsing data documenting access of said user to a set of a plurality of web documents during a pre-monitoring period that precedes said monitoring period, said deviation is at least one of an access to an additional web document that is not in said set at a respective time during said monitoring period and lack of access to at least one of said plurality of web documents at a respective time during said monitoring period.

### Claim 7 (depends on 1)

The method of claim 1, wherein said behavioral pattern is calculated by gathering media content viewed by the user during a pre monitoring period, said deviation is at least one of viewing additional media content at a respective time during said monitoring period and not viewing a routinely viewed content at a respective time during said monitoring period.

### Claim 8 (depends on 1)

The method of claim 1, wherein said behavioral pattern is an application usage pattern calculated by gathering application usage data a set of a plurality of application installed in a client terminal used by said user during a pre-monitoring period that precedes said monitoring period, said deviation is at least one of using an additional application that is not in said set at a respective time during said monitoring period and lack of usage of at least one of said plurality of applications at a respective time during said monitoring period.

### Claim 9 (depends on 1)

The method of claim 1, wherein said behavioral pattern is a communication pattern calculated by gathering communication data documenting a set of a plurality of communication sessions held using a client terminal of said user during a pre-monitoring period that precedes said monitoring period, said deviation is at least one communicating with at least one new contact, not communicating with a routinely contacted contact during said monitoring period, and changing an average time or frequency of a routinely performed communication session during said monitoring period.

### Claim 10 (depends on 9)

The method of claim 9, wherein said communication data comprises a call history indicative of calls made by or with the user during said pre-monitoring period.

### Claim 11 (depends on 9)

The method of claim 9, wherein said communication data comprises a messaging history indicative of at least one instant messaging content and instant messaging participants made during said pre-monitoring period.

### Claim 12 (depends on 9)

The method of claim 9, wherein said communication data comprises email history indicative of recipients or senders of emails sent or received during said pre monitoring period.

### Claim 13 (depends on 1)

The method of claim 1, wherein said behavioral pattern is a communication pattern calculated by gathering email data documenting a set of a plurality of communication sessions held using a client terminal of said user during a pre-monitoring period that precedes said monitoring period, said deviation is detected by identifying content not documented in said plurality of communication sessions and viewed by said user using said client terminal.

### Claim 14 (depends on 1)

The method of claim 1, wherein said monitoring period is at least 1 hour.

### Claim 15 (depends on 1)

The method of claim 1, wherein said resource is a file and said security question is embedded into a security script loaded when an access to said file is requested.

### Claim 16 (depends on 1)

The method of claim 1, wherein said resource is an application installed in a client terminal and said security question is presented when an access said application is requested.

### Claim 17

A system of dynamically generating a security question for accessing a resource, comprising:
database which stores a behavioral pattern indicative of repetitive behavior of a user;
a monitoring module which monitors a behavior of said user, as detected by a client terminal of said user during a monitoring period, to identify automatically a deviation from said behavioral pattern;
a question generation module which generates automatically a security question responded to by an indication of said deviation;
a user interface which generates a presentation of said security question and receives a user input in response to said presentation; and
an authentication module which authenticate, after said monitoring period, an access to a resource according to a match between said user input and said deviation.

### Claim 18

A computer program product for dynamically generating a security question for accessing a resource, comprising:
a computer readable storage medium;
first program instructions to monitoring a behavior of a user during a monitoring period to identify automatically a deviation from a behavioral pattern indicative of repetitive behavior of said user;
second program instructions to generate automatically a security question responded to by an indication of said deviation;
third program instructions to receive a user input in response to a presentation of said security question and said deviation; and
fourth program instructions to authenticate, after said monitoring period, an access to a resource according to a match between said user input and said deviation;
wherein said first, second, third, and fourth program instructions are stored on said computer readable storage medium.
