Authentication based on through-body signals
View Patent ↗Techniques are described for user authentication based on a signal that is transmitted through an individual's body, and detected using device(s) in physical contact with the individual. A signal, such as an electrical signal or a vibrational signal, may be transmitted from a first device and received by a second device that is in physical contact with the individual. The received signal may be employed to determine a body signature for the individual. The body signature may identify the individual among a population of individuals, given the particular alterations to the propagating signal caused by the individual's physiology. Accordingly, the body signature may be employed as a form of biometric data that is useable to authenticate the individual to access a secure area, log in to a device or an application, or for other purposes.
1. A system, comprising:
an automated teller machine (ATM) system comprising a transmitting device configured to transmit a first body area network (BAN) signal when a user is physically contacting the transmitting device;
a BAN device configured to be disposed on the user, wherein the BAN device is configured to receive a second BAN signal, wherein the first BAN signal is transmitted through a body of the user and received by the BAN device as the second BAN signal;
a client device configured to:
receive the second BAN signal from the BAN device;
generate a body signature for the user based on the second BAN signal and a model body signature associated with the user, wherein the model body signature is configured to track one or more changes to the body signature under different humidity levels; and
authenticate an identify of the user based on the body signature.
2. The system of claim 1 , wherein the client device is configured to generate the body signature based on a difference between the first BAN signal and the second BAN signal.
3. The system of claim 1 , wherein the client device is configured to generate the body signature based on a model body signature associated with the user, wherein the model body signature is configured to track one or more changes to the body signature over time.
4. The system of claim 1 , wherein the model body signature is determined based on a machine learning algorithm configured to refine the model body signature after the client device authenticates the identity of the user.
5. The system of claim 1 , wherein the client device is part of the ATM system.
6. The system of claim 1 , wherein the BAN device comprises a wearable computing device or an implanted computing device.
7. The system of claim 1 , wherein the first BAN signal comprises a vibrational signal.
8. The system of claim 1 , wherein the transmitting device is configured to transmit the first BAN signal in response to detecting that the user is within a proximity to the transmitting device.
9. A body area network (BAN) device, comprising a processor configured to execute computer-executable instructions configured to cause the processor to:
receive a first signal after being propagated through a body of an individual, wherein the first signal is altered from a second signal transmitted by a transmitting device;
determine a body signature for the individual based on the first signal and the second signal;
authenticate an identity of the individual based on the body signature and a model body signature associated with the individual, wherein the model body signature is determined based on one or more changes to the body signature over time; and
communicate an indication of the identity of the individual being authenticated to a computing device over a wireless network, wherein the computing device is configured to perform an operation in response to the identity of the individual being authenticated.
10. The BAN device of claim 9 , wherein the model body signature of the individual is stored on a server device communicatively accessible to the BAN device.
11. The BAN device of claim 9 , wherein the processor is configured to authenticate the identity of the individual based on a difference between the body signature and the model body signature.
12. The BAN device of claim 11 , wherein the processor is configured to authenticate the identity of the individual in response to the difference being greater than a threshold.
13. The BAN device of claim 9 , wherein the second signal comprises a vibrational signal.
14. The BAN device of claim 13 , wherein the first signal comprises an alteration of the second signal as the second signal propagates through a physiology of the individual.
15. A method, comprising:
receiving, via at least one processor, a first signal after being propagated through a body of an individual, wherein the first signal is altered from a second signal transmitted by a transmitting device;
determining, via the at least one processor, a body signature for the individual based on the first signal and the second signal;
authenticating, via the at least one processor, an identity of the individual based on the body signature and a model body signature associated with the individual, wherein the model body signature is determined based on one or more changes to the body signature over time; and
communicating, via the at least one processor, an indication of the identity of the individual being authenticated to a computing device over a wireless network, wherein the computing device is configured to perform an operation in response to the identity of the individual being authenticated.
16. The method of claim 15 , wherein authenticating the identity of the individual comprise sending the body signature to a server device configured to compare the body signature to the model body signature.
17. The method of claim 15 , wherein the model of the body signature is determined by:
training the model of the body signature based on biometric data associated with individual;
storing the model of the body signature in a storage component;
monitoring one or more fluctuations in the body signature as determined over time; and
adjusting the model of the body signature based on the one or more fluctuations in the body signature.
18. The method of claim 17 , wherein the biometric data comprises physiological features associated with the individual.
19. The method of claim 15 , wherein the second signal comprises a vibrational signal.