Multi-Device User Identify Validation Based on Behavioral Signal Fidelity
AssigneePlurilock Security Solutions Inc.
InventorsYoussef Nakkabi, Paulo Quinan, Jord Tanner, Ian Paterson
Life of this patent
Estimating the term…
Abstract
Various implementations disclosed herein include devices, systems, and methods that identify users based on input/sensor data. This may involve monitoring user identity using multiple signals from multiple devices (e.g., laptop keyboard, mobile device movement, facial recognition, etc.). The signals may be used to identify the user based on the current circumstances (e.g., signal fidelity). For example, the circumstances may change as one signal degrades and another signal increases in quality.
Claims20
A method comprising:
- at a processor,
- receiving a first set of one or more behavioral signals from a first electronic device, wherein the first electronic device and a second electronic device are within a set of electronic devices associated with a user, wherein the first set of one or more behavioral signals are received as the user is starting or increasing use of the second electronic device while using or after using the first electronic device;
- determining confidence in user identity by:
- determining signal-specific-scores comprising a score corresponding to confidence in user identity for each of the one or more behavioral signals of the first set;
- determining a fidelity of each of the signal-specific scores based on a rate of use of an input device associated with the first electronic device or whether the first electronic device is currently being held;
- and
- determining the confidence in user identify based on the signal-specific specific scores and the fidelity in each of the signal specific scores.
A system comprising:
- a non-transitory computer-readable storage medium;
- and
- one or more processors coupled to the non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium comprises program instructions that, when executed on the one or more processors, cause the system to perform operations comprising:
- receiving a first set of one or more behavioral signals from a first electronic device, wherein the first electronic device and a second electronic device are within a set of electronic devices associated with a user, wherein the first set of one or more behavioral signals are received as the user is starting or increasing use of the second electronic device while using or after using the first electronic device;
- determining confidence in user identity by:
- determining signal-specific-scores comprising a score corresponding to confidence in user identity for each of the one or more behavioral signals of the first set;
- determining a fidelity of each of the signal-specific scores based on a rate of use of an input device associated with the first electronic device or whether the first electronic device is currently being held;
- and
- determining the confidence in user identify based on the signal-specific specific scores and the fidelity in each of the signal specific scores.
A non-transitory computer-readable storage medium, storing instructions executable via one or more processors to perform operations comprising:
- receiving a first set of one or more behavioral signals from a first electronic device, wherein the first electronic device and a second electronic device are within a set of electronic devices associated with a user, wherein the first set of one or more behavioral signals are received as the user is starting or increasing use of the second electronic device while using or after using the first electronic device;
- determining confidence in user identity by:
- determining signal-specific-scores comprising a score corresponding to confidence in user identity for each of the one or more behavioral signals of the first set;
- determining a fidelity of each of the signal-specific scores based on a rate of use of an input device associated with the first electronic device or whether the first electronic device is currently being held;
- and
- determining the confidence in user identify based on the signal-specific specific scores and the fidelity in each of the signal specific scores.
Dependencies are inferred from the claim text.