Liveness detection based on reflections analysis

1. A computer implemented method of determining liveness of a user, comprising:

using at least one processor for:

analyzing visual content of a screen of a client device used by a user to access at least one online service;

adjusting at least one visual object displayed on the screen according to at least one dynamically changing pattern;

receiving a sequence of images depicting at least one reflecting surface associated with the user viewing the screen while the at least one visual object is displayed;

analyzing at least some images of the sequence to identify a reflection of at least part of the at least one displayed visual object in at least part of the at least one reflecting surface; and

verifying liveness of the user based on at least one of a plurality of reflection attributes of the identified reflection.

2. The method of claim 1 , wherein the at least one visual object changes over time according to the at least one dynamically changing pattern.

3. The method of claim 1 , wherein the at least one processor is further configured to adjust randomly the at least one dynamically changing pattern.

4. The method of claim 1 , wherein the at least one processor is further configured to adjust at least one display parameter of the at least one visual object according to at least one of the plurality of reflection attributes of the identified reflection.

5. The method of claim 1 , wherein the at least one processor is further configured to adjust at least one display parameter of the at least one visual object according to at least one illumination condition identified in an environment of the client device.

6. The method of claim 1 , wherein the at least one processor is further configured to adjust at least one display parameter of the at least one visual object according to at least one operational parameter of at least one imaging sensor capturing the sequence of images.

7. The method of claim 1 , wherein the at least one reflecting surface is a member of a group consisting of: an eye of the user, a lens of glasses worn by the user, a wearable item worn by the user and a reflecting object located in an environment of the user.

8. The method of claim 1 , wherein the at least one processor is further configured to verify liveness of the user based on at least one of the plurality of reflection attributes of a plurality of reflections identified in a plurality of reflecting surfaces associated with the user by:

receiving a sequence of images depicting the plurality of reflecting surfaces,

analyzing at least some images of the sequence to identify at least one of the plurality of reflection attributes of a respective one of the plurality of reflections of the at least one displayed visual object in a respective one of the plurality of reflecting surfaces,

correlating between the at least one reflection attribute identified in the plurality of reflections, and

verifying liveness of the user based on the correlation.

9. The method of claim 8 , wherein the correlation is based on a distance between the plurality of reflecting surfaces and/or the distance between at least one of the plurality of reflecting surfaces and at least one imaging sensor capturing the sequence of images.

10. The method of claim 1 , wherein the at least one visual object is a member of a group consisting of: a graphical element and a text element.

11. The method of claim 1 , wherein the at least one visual object is embedded in online content rendered by the client device.

12. The method of claim 1 , wherein the at least one visual object is embedded in visual content generated by the client device.

13. The method of claim 1 , wherein the liveness of the user is verified based on analysis of the at least some reflection attributes of the identified reflection according to at least one reflection rule.

14. The method of claim 1 , wherein the liveness is verified based on analysis of the at least some reflection attributes of the identified reflection by at least one trained machine learning (ML) model.

15. The method of claim 1 , wherein the liveness is verified to support authentication of the user using the client device for at least one of: access at least one secure online service, and engaging in a video session.

16. The method of claim 1 , wherein the at least one processor is deployed in the client device.

17. The method of claim 1 , wherein the at least one processor is deployed in a remote server in communication with the client device via at least one network.

18. A system for determining liveness of a user, comprising:

at least one processor configured to execute a code, the code comprising:

code instruction to analyze visual content of a screen of a client device used by a user to access at least one online service;

code instruction to adjust at least one visual object displayed on the screen according to at least one dynamically changing pattern;

code instruction to receive a sequence of images depicting at least one reflecting surface associated with the user viewing the screen while the at least one visual object is displayed;

code instruction to analyze at least some images of the sequence to identify a reflection of at least part of the at least one displayed visual object in at least part of the at least one reflecting surface; and

code instruction to verify liveness of the user based on at least one of a plurality of reflection attributes of the identified reflection.