Conditional behavioural biometrics
The present invention relates to an improved method of providing identification of a user or authentication of a user's identity. More particularly, the present invention relates to an improved method of providing identification of a user or authentication of a user's identity using conditional behavioural biometrics. The present invention seeks to provide an enhanced method of authenticating and/or identifying a user identity using conditional behavioural biometrics. According to a first aspect of the present invention, there is provided a method of generating a user profile for use in identifying and/or authenticating a user on a device, the device equipped with one or more sensors, the method comprising: generating a set of data points from sensory data collected by the one or more sensors; clustering the set of data points to produce a set of data clusters; developing a first classifier for the data clusters, the first classifier being operable to assign a further data point derived from a further user interaction with the computing device to one of the data clusters; and developing one or more further classifiers for at least one of the data clusters, the further classifier operable to identify and/or authenticate a user identity based on the further data point.
1. A method comprising:
(a) monitoring touch-screen gestures of a user, that interacts with an online service via a touch-screen of a computing device; and monitoring acceleration and tilt of said computing device, during said touch-screen gestures;
(b) extracting data-points from information monitored in step (a);
(c) generating a user-specific profile that indicates a characterizing acceleration and a characterizing tilt of the computing device during said touch-screen gestures;
(d) subsequently, monitoring touch-screen gestures during access to said online service, and monitoring accompanying acceleration and tilt;
(e) extracting data-points from information monitored in step (d);
(f) analyzing the data-points extracted in step (e), and checking whether said data-points match said user-specific profile generated in step (c);
(g) if the checking of step (f) has a negative result, then: generating a notification that a user that interacted in step (d) to access said online service, is different from the user that interacted in step (a) to access said online service;
wherein the generating of step (g) is further based on:
determining that a first characteristic of landscape/portrait device orientation during touch-screen gestures monitored on the computing device in step (a), is different from a second characteristic of landscape/portrait device orientation during touch-screen gestures monitored on the computing device in step (d).
2. The method of claim 1 ,
wherein the computing device is a device selected from the group consisting of:
a laptop computer, a personal computer, a desktop computer, a mobile computing device, a mobile telephone, a tablet.
3. The method of claim 1 , comprising:
utilizing user interactions with the computing device to authenticate the user identity without requiring the user to input any security data, by collecting and monitoring sensory data in the background on the computing device.
4. The method of claim 1 , comprising:
utilizing user interactions with the computing device to authenticate the user identity without requiring the user to input any security data, by collecting and monitoring sensory data in the background on the computing device;
wherein, if behavioral biometrics continue to classify the user as an authorized user, then the method does not require the user to provide any password or PIN or fingerprint and the method comprises performing user authentication in the background;
wherein, if said behavioral biometrics fail to continue to classify the user as the authorized user, then the method comprises asking the user to enter further security information.
5. The method of claim 1 ,
wherein the extracting of data-points, in at least one of step (c) and step (e), comprises:
deriving features from sensory data that includes one or more of: duration of touch-screen interaction, physical distance of touch-screen interaction, time between touch-screen interactions, deviation from a straight line during touch-screen interaction, acceleration of touch-screen interaction, deceleration of touch-screen interaction, curvature of touch-screen interaction, length of touch-screen interaction.
6. The method of claim 1 ,
wherein the extracting of data-points, in at least one of step (c) and step (e), comprises:
deriving features from sensory data that includes one or more of: duration of touch-screen interaction, physical distance of touch-screen interaction, time between touch-screen interactions, deviation from a straight line during touch-screen interaction, acceleration of touch-screen interaction, deceleration of touch-screen interaction, curvature of touch-screen interaction, length of touch-screen interaction.
7. The method of claim 1 ,
wherein the extracting of data-points, in at least one of step (c) and step (e),
is performed until data-points reach a pre-defined number of data-points that is determined to be statistically significant for performing classification that reliably identifies the user.
8. The method of claim 1 ,
wherein the extracting of data-points, in at least one of step (c) and step (e),
is performed until data-points reach a number of data-points that is chosen adaptively by a machine learning technique.
9. The method of claim 1 ,
wherein monitoring touch-screen gestures and monitoring acceleration and tilt,
in at least one of step (a) and step (d),
are performed while the user is entering user-authentication data which includes at least one of: a password, a Personal Identification Number (PIN).
10. The method of claim 1 ,
wherein monitoring touch-screen gestures and monitoring acceleration and tilt,
in at least one of step (a) and step (d),
are performed during an online check-out process of purchasing goods or services over the Internet.
11. The method of claim 1 ,
wherein generating the user-specific profile in step (c) is performed locally by a processor of said computing device.
12. The method of claim 1 ,
wherein generating the user-specific profile in step (c) is performed on a remote server which receives from the computing device at least one of: raw sensory data, derived sensory data.
13. A method comprising:
(a) monitoring touch-screen gestures of a user, that interacts with an online service via a touch-screen of a computing device; and monitoring acceleration and tilt of said computing device, during said touch-screen gestures;
(b) extracting data-points from information monitored in step (a);
(c) generating a user-specific profile that indicates a characterizing acceleration and a characterizing tilt of the computing device during said touch-screen gestures;
(d) subsequently, monitoring touch-screen gestures during access to said online service, and monitoring accompanying acceleration and tilt;
(e) extracting data-points from information monitored in step (d);
(f) analyzing the data-points extracted in step (e), and checking whether said data-points match said user-specific profile generated in step (c);
(g) if the checking of step (f) has a negative result, then: generating a notification that a user that interacted in step (d) to access said online service, is different from the user that interacted in step (a) to access said online service;
wherein the generating of step (g) is comprises:
generating a user-specific profile that is based on at least:
(I) a characteristic of background tremor of the computing device during monitored touch-screen gestures, and
(II) a characteristic of curvature of monitored touch-screen gestures, and
(III) a characteristic of landscape/portrait device orientation during monitored touch-screen gestures.
14. The method of claim 13 ,
wherein the computing device is a device selected from the group consisting of:
a laptop computer, a personal computer, a desktop computer, a mobile computing device, a mobile telephone, a tablet.
15. The method of claim 13 , comprising:
utilizing user interactions with the computing device to authenticate the user identity without requiring the user to input any security data, by collecting and monitoring sensory data in the background on the computing device.
16. The method of claim 13 , comprising:
utilizing user interactions with the computing device to authenticate the user identity without requiring the user to input any security data, by collecting and monitoring sensory data in the background on the computing device;
wherein, if behavioral biometrics continue to classify the user as an authorized user, then the method does not require the user to provide any password or PIN or fingerprint and the method comprises performing user authentication in the background;
wherein, if said behavioral biometrics fail to continue to classify the user as the authorized user, then the method comprises asking the user to enter further security information.
17. A method comprising:
(a) monitoring touch-screen gestures of a user, that interacts with an online service via a touch-screen of a computing device; and monitoring acceleration and tilt of said computing device, during said touch-screen gestures;
(b) generating a user-specific profile that is based on at least: (i) device tremor during user interactions, and (ii) device orientation as portrait or landscape during user interactions;
(c) subsequently, monitoring touch-screen gestures and monitoring acceleration and tilt; and checking whether touch-screen gestures and acceleration and tilt match the user-specific profile generated in step (b);
(d) if the checking of step (c) has a negative result, then: generating a notification that a user that interacted in step (c) to access said online service, is different from the user that interacted in step (a) to access said online service.
18. The method of claim 17 ,
wherein the computing device is a device selected from the group consisting of:
a laptop computer, a personal computer, a desktop computer, a mobile computing device, a mobile telephone, a tablet.
19. The method of claim 17 , comprising:
utilizing user interactions with the computing device to authenticate the user identity without requiring the user to input any security data, by collecting and monitoring sensory data in the background on the computing device.
20. The method of claim 17 , comprising:
utilizing user interactions with the computing device to authenticate the user identity without requiring the user to input any security data, by collecting and monitoring sensory data in the background on the computing device;
wherein, if behavioral biometrics continue to classify the user as an authorized user, then the method does not require the user to provide any password or PIN or fingerprint and the method comprises performing user authentication in the background;
wherein, if said behavioral biometrics fail to continue to classify the user as the authorized user, then the method comprises asking the user to enter further security information.
21. A system comprising:
a hardware processor which is configured to
(a) monitor touch-screen gestures of a user, that interacts with an online service via a touch-screen of a computing device; and monitor acceleration and tilt of said computing device, during said touch-screen gestures;
(b) extract data-points from information monitored in step (a);
(c) generate a user-specific profile that indicates a characterizing acceleration and a characterizing tilt of the computing device during said touch-screen gestures;
(d) subsequently, monitor touch-screen gestures during access to said online service, and monitor accompanying acceleration and tilt;
(e) extract data-points from information monitored in step (d);
(f) analyze the data-points extracted in step (e), and check whether said data-points match said user-specific profile generated in step (c);
(g) if the check of step (f) has a negative result, then: generate a notification that a user that interacted in step (d) to access said online service, is different from the user that interacted in step (a) to access said online service;
wherein the hardware processor is configured to determine that a first characteristic of landscape/portrait device orientation during touch-screen gestures monitored on the computing device in step (a), is different from a second characteristic of landscape/portrait device orientation during touch-screen gestures monitored on the computing device in step (d).
22. The system of claim 21 ,
wherein the system is configured to utilize user interactions with the computing device to authenticate the user identity without requiring the user to input any security data, by collecting and monitoring sensory data in the background on the computing device.
23. A system comprising:
a hardware processor that is adapted to
(a) monitor touch-screen gestures of a user, that interacts with an online service via a touch-screen of a computing device; and monitor acceleration and tilt of said computing device, during said touch-screen gestures;
(b) extract data-points from information monitored in step (a);
(c) generate a user-specific profile that indicates a characterizing acceleration and a characterizing tilt of the computing device during said touch-screen gestures;
(d) subsequently, monitor touch-screen gestures during access to said online service, and monitor accompanying acceleration and tilt;
(e) extract data-points from information monitored in step (d);
(f) analyze the data-points extracted in step (e), and check whether said data-points match said user-specific profile generated in step (c);
(g) if the check of step (f) has a negative result, then: generate a notification that a user that interacted in step (d) to access said online service, is different from the user that interacted in step (a) to access said online service;
wherein the processor is adapted to
generate a user-specific profile that is based on at least:
(i) a characteristic of background tremor of the computing device during monitored touch-screen gestures, and
(ii) a characteristic of curvature of monitored touch-screen gestures, and
(iii) a characteristic of landscape/portrait device orientation during monitored touch-screen gestures.
24. The system of claim 23 ,
wherein the system is configured to utilize user interactions with the computing device to authenticate the user identity without requiring the user to input any security data, by collecting and monitoring sensory data in the background on the computing device.
25. A system comprising:
a hardware processor that is configured to
(a) monitor touch-screen gestures of a user, that interacts with an online service via a touch-screen of a computing device; and monitor acceleration and tilt of said computing device, during said touch-screen gestures;
(b) generate a user-specific profile that is based on at least: (i) device tremor during user interactions, and (ii) device orientation as portrait or landscape during user interactions;
(c) subsequently, monitor touch-screen gestures and monitoring acceleration and tilt; and check whether touch-screen gestures and acceleration and tilt match the user-specific profile generated in step (b);
(d) if the check of step (c) has a negative result, then: generate a notification that a user that interacted in step (c) to access said online service, is different from the user that interacted in step (a) to access said online service.
26. The system of claim 25 ,
wherein the system is configured to utilize user interactions with the computing device to authenticate the user identity without requiring the user to input any security data, by collecting and monitoring sensory data in the background on the computing device.