Biometric authentication techniques
Techniques are disclosed relating to biometric authentication, e.g., facial recognition. In some embodiments, a device is configured to verify that image data from a camera unit exhibits a pseudo-random sequence of image capture modes and/or a probing pattern of illumination points (e.g., from lasers in a depth capture mode) before authenticating a user based on recognizing a face in the image data. In some embodiments, a secure circuit may control verification of the sequence and/or the probing pattern. In some embodiments, the secure circuit may verify frame numbers, signatures, and/or nonce values for captured image information. In some embodiments, a device may implement one or more lockout procedures in response to biometric authentication failures. The disclosed techniques may reduce or eliminate the effectiveness of spoofing and/or replay attacks, in some embodiments.
1. An apparatus, comprising:
a camera unit;
one or more processing elements configured to:
determine a pseudo-random sequence of image capture modes for a plurality of groups of image captures, wherein each group includes at least a capture using a first illumination mode and a capture using a second illumination mode, wherein the ordering of the first and second illumination modes for each group is pseudo-randomly determined;
receive image information for a set of image captures, wherein the image information is indicated as being captured by the camera unit; and
determine whether to authorize facial recognition in response to analyzing the image information and determining whether the image information was captured using the pseudo-random sequence of image capture modes.
2. The apparatus of claim 1 , wherein the first illumination mode uses flood illumination and the second illumination mode uses multiple discrete points of illumination and each group is a pair of captures using the first illumination mode and the second illumination mode.
3. The apparatus of claim 2 , wherein the second illumination mode uses vertical-cavity surface-emitting laser (VCSEL) illumination to determine depth.
4. The apparatus of claim 1 , wherein the one or more processing elements include a secure circuit, wherein the apparatus is configured not to allow access to hardware resources of the secure circuit other than via messages sent to a predefined set of one or more memory locations; and
wherein the secure circuit is configured to determine whether the image information was captured using the pseudo-random sequence of image capture modes.
5. The apparatus of claim 4 , wherein the secure circuit is configured to generate a different cryptographic nonce for ones of different facial recognition sessions, provide a cryptographic nonce to the camera unit, and confirm that each image in the sequence includes the cryptographic nonce.
6. The apparatus of claim 5 , wherein the secure circuit is configured to communicate with the camera unit using an elliptic curve Diffie-Hellman (ECDH) session and wherein the secure element is configured to use a different ECDH exchanged secret key for communications during each of multiple different facial recognition sessions with the camera unit.
7. The apparatus of claim 5 , wherein the secure circuit is configured to verify signature information for frames of image data in a facial recognition session, wherein the signature information is generated by the camera unit using a secret key.
8. The apparatus of claim 5 , wherein the secure circuit is configured to verify frame count information for frames of image data captured during a facial recognition session.
9. The apparatus of claim 1 , wherein the one or more processing elements are configured to communicate with the camera unit via a dedicated bus and wherein the apparatus is configured to require a user to manually enter one or more authentication credentials to access the apparatus in response to a disconnect of the dedicated bus.
10. A method, comprising:
determining, by a computing device, a pseudo-random sequence of image capture modes for a plurality of groups of image captures, wherein each group includes at least captures using a first illumination mode and a second illumination mode, wherein the ordering of the first and second illumination modes for each pair is pseudo-randomly determined;
receiving, by circuitry of the computing device, image information indicated as being captured by a known camera unit; and
determining, by the circuitry, whether to authorize facial recognition in response to analyzing the image information and determining whether the image information was captured using the pseudo-random sequence of image capture modes.
11. The method of claim 10 , wherein the first illumination mode uses flood illumination and the second illumination mode uses multiple discrete points of illumination.
12. The method of claim 10 , wherein the circuitry is a secure circuit and the computing device is configured not to allow access to hardware resources of the secure circuit other than via messages sent to a predefined set of one or more memory locations.
13. The method of claim 10 , further comprising:
generating, by the circuitry, a different cryptographic nonce for ones of different facial recognition sessions;
providing a cryptographic nonce to the camera unit; and
confirming that each image in the sequence includes the cryptographic nonce.
14. The method of claim 10 , further comprising:
using, by the circuitry, a different ECDH exchanged secret key for communications during each of multiple different facial recognition sessions with a camera unit of the computing device.
15. The method of claim 10 , further comprising:
requiring a user to manually enter one or more authentication credentials to access the computing device in response to a disconnect of a bus used to communicate with a camera unit of the computing device.
16. A non-transitory computer readable storage medium having stored thereon design information that specifies a design of at least a portion of a hardware integrated circuit in a format recognized by a semiconductor fabrication system that is configured to use the design information to produce the circuit according to the design, including:
one or more processing elements configured to:
determine a pseudo-random sequence of image capture modes for a plurality of groups of image captures, wherein each group includes a capture using a first illumination mode and a capture using a second illumination mode, wherein the ordering of the first and second illumination modes for each pair is pseudo-randomly determined;
receive image information for a set of image captures by a camera unit; and
determine whether to authorize facial recognition in response to analyzing the image information and determining whether the image information was captured using the pseudo-random sequence of image capture modes.
17. The non-transitory computer readable storage medium of claim 16 , wherein the first illumination mode uses flood illumination and the second illumination mode uses multiple discrete points of illumination.
18. The non-transitory computer readable storage medium of claim 16 , wherein the one or more processing elements include a secure circuit, wherein the circuit is configured not to allow access to hardware resources of the secure circuit other than via messages sent to a predefined set of one or more memory locations; and
wherein the secure circuit is configured to determine whether the image information was captured using the pseudo-random sequence of image capture modes.
19. The non-transitory computer readable storage medium of claim 18 , wherein the secure circuit is configured to verify signature information for frames of image data in a facial recognition session, wherein the signature information is generated by a camera unit using a secret key.
20. The non-transitory computer readable storage medium of claim 18 , wherein the secure circuit is configured to generate a different cryptographic nonce for ones of different facial recognition sessions, provide a cryptographic nonce to a camera unit, and confirm that each image in the sequence includes the cryptographic nonce.