User authentication using a mobile device

A non-transitory machine-readable medium, comprising executable instructions that, when executed by a processor, facilitate performance of operations, comprising:

• determining an input received via a mobile device, wherein the input received at the mobile device comprises an application accessed for a threshold amount of time during a defined time window, activities correlated to the application over time, reactions correlated to the application over time, or a combination thereof, and wherein the application runs on the mobile device;
• determining, based on the input and using an authentication model, whether the input matches an input pattern associated with an authorized user profile authorized to access a feature of the mobile device, wherein the input pattern has been determined based on machine learning applied to past inputs at the mobile device other than the input, and wherein the authentication model has been generated based on the machine learning applied to the input pattern, wherein the past inputs at the mobile device are determined using a tracking cookie installed on the mobile device;
• and
• based on a determination that the input at the mobile device is associated with the authorized user profile, granting access to the feature of the mobile device.

A method, comprising:

• determining, by a processing system including a processor, an input received at a mobile device, wherein the input received at the mobile device comprises an application accessed for a threshold amount of time during a defined time window, activities correlated to the application over time, reactions correlated to the application over time, or a combination thereof, and wherein the application runs on the mobile device;
• determining, by the processing system, based on the input and using an authentication model, whether the input matches an input pattern associated with an authorized user profile, wherein the input pattern has been determined based on machine learning applied to past inputs at the mobile device other than the input, and wherein the authentication model has been further generated based on the machine learning applied to the input pattern;
• and
• based on a determination that the input does not match the input pattern, blocking, by the processing system, access to a feature of the mobile device.