Method, device, and system of differentiating among users based on user classification

Patent metadata

Field	Value
Publication number	US-9703953-B2
Application number	US-201514675770-A
Country	US
Kind code	B2
Filing date	Apr 1, 2015
Priority date	Nov 29, 2010
Publication date	Jul 11, 2017
Grant date	Jul 11, 2017

Abstract

Devices, systems, and methods of detecting user identity, differentiating between users of a computerized service, and detecting a cyber-attacker. An end-user device interacts and communicates with a server of a computerized server (a banking website, an electronic commerce website, or the like). The interactions are monitored, tracked and logged. User Interface (UI) interferences or irregularities are introduced; and the server tracks the response or the reaction of the end-user to such interferences. The system determines whether the user is a legitimate user, or a cyber-attacker or automated script posing as the legitimate user. The system utilizes classification of users into classes or groups, to deduce or predict how a group-member would behave when accessing the service through a different type of device. The system identifies user-specific traits that are platform-independent and thus can be further monitored when the user switches from a first platform to a second platform.

First claim

What is claimed is:

1. A method comprising:
(a) monitoring input-unit interactions of a plurality of users, wherein each user of said plurality of users separately utilizes an electronic device to access a computerized service;
(b) clustering a first user, a second user, and a third user of said plurality of users into a particular cluster of users whose input-unit interactions exhibit a particular behavioral trait when they interact with said computerized service through a portable electronic device;
(c) subsequently, detecting that the first user and the second user, access said computerized service via a non-portable electronic device, in a manner that exhibits a second, different, behavioral trait;
(d) determining that the third user is also expected to exhibit said second behavioral trait when the third user accesses said computerized service via a non-portable electronic device;
(e) in a particular usage session, in which said third user firstly-ever accesses the computerized service via a non-portable electronic device: if said particular usage session of said third user, does not exhibit said second behavioral trait that was determined in steps (c) and (d), then, determining that said particular usage session is attributed to a cyber-attacker and not to said third user;
wherein the method comprises:
based on steps (a) and (b) and (c) and (d), and prior to the third user ever accessing the computerized service via a non-portable electronic device,
generating a differentiation rule that predicts that the third user, during his first-ever access to the computerized service via the non-portable electronic device, would perform user interactions that exhibit said second behavioral trait which was never yet observed in any monitored input-units interactions of the third user.

2. The method of claim 1 , wherein the determining of step (d) is performed prior to the third user ever accessing the computerized service via a non-portable electronic device.

3. A method comprising:
(a) monitoring input-unit interactions of a plurality of users, wherein each user of said plurality of users separately utilizes an electronic device to access a computerized service;
(b) clustering a first user, a second user, and a third user of said plurality of users, into a particular cluster of users whose input-unit interactions exhibit a particular behavioral trait when they interact with said computerized service through a non-portable electronic device;
(c) subsequently, detecting that the first user and the second user, access said computerized service via a portable electronic device, in a manner that exhibits a second, different, behavioral trait;
(d) determining that the third user is also expected to exhibit said second behavioral trait when the third user accesses said computerized service via a portable electronic device;
(e) in a particular usage session, in which said third user firstly-ever accesses the computerized service via a portable electronic device: if said particular usage session of said third user, does not exhibit said second behavioral trait that was determined in steps (c) and (d), then, determining that said particular usage session is attributed to a cyber-attacker and not to said third user;
wherein the method comprises:
based on steps (a) and (b) and (c) and (d), and prior to the third user ever accessing the computerized service via a non-portable electronic device,
generating a differentiation rule that predicts that the third user, during his first-ever access to the computerized service via the non-portable electronic device, would perform user interactions that exhibit said second behavioral trait which was never yet observed in any monitored input-units interactions of the third user.

4. The method of claim 3 , wherein the determining of step (c) is performed prior to the third user ever accessing the computerized service via a non-portable electronic device.

5. A process comprising:
(a) monitoring input-unit interactions of a plurality of users, wherein each user of said plurality of users separately utilizes an electronic device to access a computerized service;
(b) clustering a first user, a second user, and a third user of said plurality of users, into a particular cluster of users whose input-unit interactions exhibit a particular behavioral trait when they interact with said computerized service through a smartphone;
(c) subsequently, detecting that the first user and the second user, access said computerized service via a computer, in a manner that exhibits a second, different, behavioral trait;
(d) determining that the third user is also expected to exhibit said second behavioral trait when the third user accesses said computerized service via a computer;
(e) in a particular usage session, in which said third user firstly-ever accesses the computerized service via a computer: if said particular usage session of said third user, does not exhibit said second behavioral trait that was determined in steps (c) and (d), then, determining that said particular usage session is attributed to a cyber-attacker and not to said third user;
wherein the process comprises:
based on steps (a) and (b) and (c) and (d), and prior to the third user ever accessing the computerized service via a computer,
generating a differentiation rule that predicts that the third user, during his first-ever access to the computerized service via a computer, would perform user interactions that exhibit said second behavioral trait which was never yet observed in any monitored input-units interactions of the third user.

6. The process of claim 5 , wherein the determining of step (c) is performed prior to the third user ever accessing the computerized service via a computer.

7. A process comprising:
(a) monitoring input-unit interactions of a plurality of users, wherein each user of said plurality of users separately utilizes an electronic device to access a computerized service;
(b) clustering a first user, a second user, and a third user of said plurality of users, into a particular cluster of users whose input-unit interactions exhibit a particular behavioral trait when they interact with said computerized service through a first-type of end-user-device;
(c) subsequently, detecting that the first user and the second user, access said computerized service via a second-type of end-user device, in a manner that exhibits a second, different, behavioral trait;
(d) determining that the third user is also expected to exhibit said second behavioral trait when the third user accesses said computerized service via said second-type of end-user-device;
(e) in a particular usage session, in which said third user firstly-ever accesses the computerized service via said second-type of end-user-device: if said particular usage session of said third user; does not exhibit said second behavioral trait that was determined in steps (c) and (d), then, determining that said particular usage session is attributed to a cyber-attacker and not to said third user;
wherein the process comprises:
based on steps (a) and (b) and (c) and (d), and prior to the third user ever accessing he computerized service via said second-type of end-user-device,
generating a differentiation rule that predicts that the third user, during his first-ever access to the computerized service via said second-type of end-user-device, would perform user interactions that exhibit said second behavioral trait which was never yet observed in any monitored input-units interactions of the third user.

8. The process of claim 7 , wherein the determining of step (c) is performed prior to the third user ever accessing the computerized service via said second-type of end-user-device.

Assignees

• Biocatch Ltd

Inventors

• Turgeman Avi
• Rivner Uri

Classifications

• G06F2221/034

  Test or assess a computer or a system · CPC title

• G06F21/554 Primary

  involving event detection and direct action · CPC title

• G06F21/31

  User authentication · CPC title

• G06F3/041

  Digitisers, e.g. for touch screens or touch pads, characterised by the transducing means · CPC title

• H04L63/102

  Entity profiles · CPC title