Learning system for virtual private network orchestration, anonymization and quality of service
A security server assigns users sessions to a provider that provides virtual private networks. The security server trains a machine-learned model to identify a provider from a set of providers. The security server obtains connection parameters associated with a requested VPN connection. Connection parameters comprise a location of a computing device that requested the VPN connection, a time of the requested VPN connection, a current and/or historical state of VPN performance data, and user preferences. The security server applies the machine-learned model to the connection parameters to identify a provider. The security server provisions a user session based on the provider and establishes a connection through the provider.
1. A computer-implemented method for assigning user sessions to a VPN service provider, the method comprising:
training a machine-learned model to identify a VPN provider from a set of VPN providers, wherein the machine-learned model is trained on historical connection parameters for a plurality of VPN providers, times, and geographic locations of VPN connections;
obtaining connection parameters associated with a requested VPN connection;
applying the machine-learned model to the connection parameters to identify a selected VPN provider;
provisioning a user session based on the selected VPN provider; and
establishing a VPN connection to the selected VPN provider.
2. The computer-implemented method of claim 1 , wherein the connection parameters comprise one or more of a location of a computing device that requested the VPN connection, a time of the requested VPN connection, a current and/or historical state of VPN performance data, and user preferences.
3. The computer-implemented method of claim 1 , wherein a computing device hosting the user session is connected to a first server in a first geographic region and the selected VPN provider is associated with servers in the first geographic region, the method further comprising:
responsive to detecting that servers in the first geographic region are down:
applying the machine-learned model to connection parameters associated with the user session to identify a second VPN provider, wherein the second VPN provider is associated with servers in a second geographic region different from the first geographic region, and
establishing a second VPN connection to the second VPN provider for the user session.
4. The computer-implemented method of claim 3 , wherein connection parameters associated with the user session include user preferences specifying the first geographic region and the second geographic region.
5. The computer-implemented method of claim 1 , wherein a computing device hosting the user session is connected to a first server, the method further comprising:
responsive to detecting that the first server is down:
applying the machine-learned model to connection parameters associated with the user session to identify a second VPN provider, and
establishing a second VPN connection to the second VPN provider for the user session.
6. The computer-implemented method of claim 1 , wherein the machine-learned model is applied to parameters comprising availability at the second VPN provider at a current time, performance at the second VPN provider at the current time, and quality of service of the second VPN provider at the current time.
7. The computer-implemented method of claim 1 , wherein the user session is multiplexed between a plurality of the set of VPN providers for a duration of the user session.
8. The computer-implemented method of claim 1 , wherein the user session is associated with a user and a first computing device, the method further comprising:
receiving, from a second computing device associated with the user, a request for a new VPN connection;
provisioning a second user session to a second VPN provider of the set of VPN providers, the second VPN provider different from the VPN provider; and
establishing a new VPN connection between the second computing device and the second VPN provider.
9. A non-transitory computer-readable storage medium comprising instructions executable by a processor, the instructions comprising:
instructions for training a machine-learned model to identify a VPN provider from a set of VPN providers, wherein the machine-learned model is trained on historical connection parameters for a plurality of VPN providers, times, and geographic locations of VPN connections;
instructions for obtaining connection parameters associated with a requested VPN connection;
instructions for applying the machine-learned model to the connection parameters to identify a selected VPN provider;
instructions for provisioning a user session based on the selected VPN provider; and
instructions for establishing a VPN connection to the selected VPN provider.
10. The non-transitory computer-readable storage medium of claim 9 , wherein the connection parameters comprise one or more of a location of a computing device that requested the VPN connection, a time of the requested VPN connection, a current and/or historical state of VPN performance data, and user preferences.
11. The non-transitory computer-readable storage medium of claim 9 , wherein a computing device hosting the user session is connected to a first server in a first geographic region and the selected VPN provider is associated with servers in the first geographic region, the instructions further comprising:
responsive to detecting that servers in the first geographic region are down:
instructions for applying the machine-learned model to connection parameters associated with the user session to identify a second VPN provider, wherein the second VPN provider is associated with servers in a second geographic region different from the first geographic region, and
instructions for establishing a second VPN connection to the second VPN provider for the user session.
12. The non-transitory computer-readable storage medium of claim 11 , wherein connection parameters associated with the user session include user preferences specifying the first geographic region and the second geographic region.
13. The non-transitory computer-readable storage medium of claim 9 , wherein a computing device hosting the user session is connected to a first server, the method further comprising:
responsive to detecting that the first server is down:
instructions for applying the machine-learned model to connection parameters associated with the user session to identify a second VPN provider, and
instructions for establishing a second VPN connection to the second VPN provider for the user session.
14. The non-transitory computer-readable storage medium of claim 13 , wherein the machine-learned model is applied to parameters comprising availability at the second VPN provider at a current time, performance at the second VPN provider at the current time, and quality of service of the second VPN provider at the current time.
15. The non-transitory computer-readable storage medium of claim 9 , wherein the user session is multiplexed between a plurality of the set of VPN providers for a duration of the user session.
16. The non-transitory computer-readable storage medium of claim 9 , wherein the user session is associated with a user and a first computing device, the instructions further comprising:
instructions for receiving, from a second computing device associated with the user, a request for a new VPN connection;
instructions for provisioning a second user session to a second VPN provider of the set of VPN providers, the second VPN provider different from the VPN provider; and
instructions for establishing a new VPN connection between the second computing device and the second VPN provider.
17. A computer system comprising:
a computer processor; and
a non-transitory computer-readable storage medium storing instructions that when executed by the computer processor perform actions comprising:
training a machine-learned model to identify a VPN provider from a set of VPN providers, wherein the machine-learned model is trained on historical connection parameters for a plurality of VPN providers, times, and geographic locations of VPN connections;
obtaining connection parameters associated with a requested VPN connection;
applying the machine-learned model to the connection parameters to identify a selected VPN provider;
provisioning a user session based on the selected VPN provider; and
establishing a VPN connection to the selected VPN provider.
18. The computer system of claim 17 , wherein the connection parameters comprise one or more of a location of a computing device that requested the VPN connection, a time of the requested VPN connection, a current and/or historical state of VPN performance data, and user preferences.
19. The computer system of claim 17 , wherein a computing device hosting the user session is connected to a first server in a first geographic region and the selected VPN provider is associated with servers in the first geographic region, the actions further comprising:
responsive to detecting that servers in the first geographic region are down:
applying the machine-learned model to connection parameters associated with the user session to identify a second VPN provider, wherein the second VPN provider is associated with servers in a second geographic region different from the first geographic region, and
establishing a second VPN connection to the second VPN provider for the user session.
20. The computer system of claim 19 , wherein connection parameters associated with the user session include user preferences specifying the first geographic region and the second geographic region.