Method for confirming the identity of a user in a browsing session of an online service

1 . A method for confirming the identity of a user in a browsing session of an online service, comprising the steps of:

a) providing a web server in which an online service resides, the web server being in communication with at least one client device provided with at least one user interface;

b) providing a database associated with the web server in which a plurality of data relating to one or more users registered to the online service are stored;

c) providing a script residing on the client device;

d) identifying via the script each browsing session on the online service and associating it with a user registered to the online service when said user performs authentication;

e) collecting via the script biometric data generated by said at least one user interface and associating them with the authenticated user, the biometric data comprising one or more sets of sensitive data chosen from a typing pattern on a keyboard of the user interface, a movement pattern of the cursor of the user interface, and a usage pattern of the user interface;

f) generating machine learning templates via the script as a result of processing biometric data;

g) storing biometric data and machine learning templates locally in the client device such that sensitive biometric data are in no way shared outside the environment of the client device as they are not sent to the web server;

h) generating a score associated with the user as a result of the processing via the script of new biometric data collected on said at least one user interface based on the machine learning templates generated in step f);

i) sending only the score to the web server, such that there is no sharing of the sensitive biometric data with the web server; and

l) verifying the identity of the authenticated user as a result of the score processing by means of a security algorithm residing on the web server.

2 . The method for confirming the identity of a user in a browsing session according to claim 1 , wherein step h) of generating a score associated with the user comprises the sub-step of attributing to the score a value between 0 and 1, where 0 represents a difference between the expected identity and the one calculated for the user using the machine learning templates, while 1 represents an exact association between the expected and calculated identity for the user using the machine learning templates.

3 . The method for confirming the identity of a user in a browsing session according to claim 1 , wherein step l) of verifying the identity of the authenticated user comprises the sub-step of generating a danger signal via the web server when the score value exceeds a predefined threshold value.

4 . The method for confirming the identity of a user in a browsing session according to claim 3 , comprising the step of m) activating security countermeasures on the client device when the web server generates the danger signal.

5 . The method for confirming the identity of a user in a browsing session according to claim 4 , wherein the security countermeasures comprise one or more among blocking the user's login, requesting a Strong Customer Authentication, blocking one or more transactions or actions performed by the user in the browsing session, and informing the user about his access at risk.

6 . The method for confirming the identity of a user in a browsing session according to claim 1 , wherein step i) of sending the score to the web server, comprises the sub-step of:

generating via said script technical data relating to the browsing of the client device on the online service and sending it to the web server together with the score.

7 . The method for confirming the identity of a user in a browsing session according to claim 6 , wherein the technical data comprise one or more among the user name used in accessing the online service, browsing session ID, client device fingerprint, network data.

8 . The method for confirming the identity of a user in a browsing session according to claim 1 , wherein step f) of generating machine learning templates via script comprises the sub-step of:

generating the machine learning templates through one or more artificial intelligence algorithms or through, or in combination with, heuristic algorithms and logical processes based on preset rules.

9 . The method for confirming the identity of a user in a browsing session according to claim 1 , wherein the script comprises a script agent executable within a web browser of the client device, or a client library executable within a mobile application of the client device.

10 . The method for confirming the identity of a user in a browsing session according to claim 1 , wherein step g) of locally storing biometric data and machine learning templates in the client device comprises the sub-step of:

storing the biometric data and the machine learning templates in a local memory of the client device or in the LocalStorage of the web browser of the client device.