# US 2026/0100842 A1 · Systems and methods for privacy-enabled biometric processing

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0100842 A1
- Document ID: US20260100842A1
- Status: Published application
- Kind: A1
- Application number: 19/213,476
- Filed: 2025-05-20
- Published: 2026-04-09
- Earliest claimed: 2018-03-07
- Assignees: Private Identity LLC
- Applicants: Private Identity LLC
- Inventors: Scott Edward Streit
- Web page: https://patentgrep.com/patent/US20260100842A1

## CPC

- H04L 9/3231: {Biological data, e.g. fingerprint, voice or retina (network architectures or network communication protocols for supporting authentication of entities using biometrical features in a packet data network H04L63/0861)}
- G06F 7/02: Comparing digital values (G06F7/06, {G06F7/22,} G06F7/38 take precedence)
- G06F 7/5443: {Sum of products (for applications thereof, see the relevant places, e.g. G06F17/10, H03H17/00)}
- G06F 21/32: using biometric data, e.g. fingerprints, iris scans or voiceprints
- G06F 21/6245: {Protecting personal data, e.g. for financial or medical purposes}
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/08: Learning methods
- G06N 3/082: modifying the architecture, e.g. adding, deleting or silencing nodes or connections
- G06N 3/09: Supervised learning
- H04L 63/0428: {wherein the data content is protected, e.g. by encrypting or encapsulating the payload}
- H04L 63/0861: {using biometrical features, e.g. fingerprint, retina-scan (cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231)}
- H04W 12/00: Security arrangements; Authentication; Protecting privacy or anonymity
- H04W 12/06: Authentication
- H04W 12/68: Gesture-dependent or behaviour-dependent
- G06F 2207/4824: Neural networks
- G06F 2221/2133: Verifying human interaction, e.g., Captcha
- G06N 3/048: Activation functions
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06N 20/20: Ensemble learning
- H04L 2209/42: Anonymization, e.g. involving pseudonyms
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)

## Abstract

A set of distance measurable encrypted feature vectors can be derived from any biometric data and/or physical or logical user behavioral data, and then using an associated deep neural network (“DNN”) on the output (i.e., biometric feature vector and/or behavioral feature vectors, etc.) an authentication system can determine matches or execute searches on encrypted data. Behavioral or biometric encrypted feature vectors can be stored and/or used in conjunction with respective classifications, or in subsequent comparisons without fear of compromising the original data. In various embodiments, the original behavioral and/or biometric data is discarded responsive to generating the encrypted vectors. In another embodiment, distance measurable or homomorphic encryption enables computations and comparisons on cypher-text without decryption of the encrypted feature vectors. Security of such privacy enabled embeddings can be increased by implementing an assurance factor (e.g., liveness) to establish a submitted credential has not been spoofed or faked.

## Claims

### Claim at position 1

-17. (canceled)

### Claim 18

A privacy-enabled authentication system comprising:
at least one processor operatively connected to a memory, the at least one processor configured to:
execute machine learning (“ML”) functionality responsive to an authentication mode;
based on executing a first authentication mode:
access an identity token for an entity to be identified or authenticated, wherein the identity token is generated based, at least in part, on input of plain text biometric or behavioral data to at least a first neural network;
classify the identity token as part of identification or authentication, including operations to predict matches using the identity token and a plurality of identification classes;
based on a executing a second authentication mode:
accept plain text biometric or behavioral data as input into the first neural network to output, at least in part, respective identity tokens;
generate an identification match based, at least in part, on comparing distances between the respective identity tokens and a plurality of identification classes that are based on, at least in part, prior identity tokens generated for respective entities, to determine the match to an identity; and
validate that identification results produced are based on live submission from a live entity, the validation including operations to determine liveness in multiple dimensions including at least a liveness evaluation of identification or authentication inputs submitted during the first authentication mode and the second authentication mode during the identification or authentication as part of the evaluation of the multiple dimensions.

### Claim 19 (depends on 18)

The system of claim 18, wherein the first authentication mode is configured to accept the identity token and label inputs during training of one or more first classification neural networks to define the plurality of identification classes.

### Claim 20 (depends on 18)

The system of claim 18, wherein one of the first authentication mode or the second authentication mode is configured to:
determine one or more distances between identity tokens produced, at least in part, by respective generation neural networks;
exclude identity tokens produced by respective generation neural networks having one or more distances exceeding a threshold distance from subsequent training processes; and
include identity tokens having distances within the threshold distance for subsequent training processes.

### Claim 21 (depends on 20)

The system of claim 20, wherein the at least one processor is configured to determine the authentication mode includes an enrollment mode for establishing a new entity for subsequent authentication.

### Claim 22 (depends on 21)

The system of claim 21, wherein the at least one processor is configured to trigger at least the second authentication mode responsive to determining a current authentication mode includes the enrollment mode.

### Claim 23 (depends on 21)

The system of claim 21, wherein the at least one processor is configured to trigger at least training operations of one or both the first and second authentication mode responsive to determining that the current authentication mode includes the enrollment mode.

### Claim 24 (depends on 23)

The system of claim 23, wherein the at least one processor is configured to execute at least the second authentication mode to authenticate a new user until at least a period of time required for training one or more first classification neural networks expires.

### Claim 25 (depends on 23)

The system of claim 23, wherein the at least one processor is configured to execute at least the first authentication mode to authenticate a new user responsive to completing training of one or more first classification neural networks.

### Claim 26 (depends on 18)

The system of claim 18, wherein one or more first classification neural networks comprise a deep neural network (“DNN”), wherein the DNN is configured to:
generate an array of values in response to the input of the at least one unclassified encrypted feature vector during authentication; and
determine a label or unknown result based on analyzing the generated array of values.

### Claim 27 (depends on 18)

The system of claim 18, wherein the generation neural networks comprise at least one learning network configured to accept plain text biometric as input and generate, at least in part, respective identity tokens as output.

### Claim 28 (depends on 18)

The system of claim 18, wherein the one or more first classification neural networks are configured to return a label for identification or an unknown result, responsive to input of a respective identity token.

### Claim 29 (depends on 18)

The system of claim 18, wherein the at least one processor is configured to:
determine a probability of match using the first or second authentication mode is below a threshold value; and
validate an unknown result based on distance analysis of a highest probability match compared to a respective identity token.

### Claim 30

A computer implemented method for privacy-enabled authentication, the method comprising
executing, by at least one processor, machine learning (“ML”) functionality responsive to an authentication mode;
accessing, by the at least one processor, an identity token for an entity to be identified or authenticated, wherein the identity token is generated based, at least in part, on input of plain text biometric or behavioral data to at least a first neural network in response to executing a first authentication mode;
classifying, by the at least one processor, the identity token as part of identification or authentication, including operations to predict matches using the identity token and a plurality of identification classes as part of the first authentication mode;
accepting, by the at least one processor, plain text biometric or behavioral data as input into the first neural network to output, at least in part, respective identity tokens in response to executing a second authentication mode;
generating, by the at least one processor, an identification match based, at least in part, on comparing distances between the respective identity tokens and a plurality of identification classes that are based on, at least in part, prior identity tokens generated for respective entities, to determine the match to an identity; and
validating, by the at least one processor, identification results produced are based on live submission from a live entity, the validation including operations to determine liveness in multiple dimensions including at least a liveness evaluation of identification or authentication inputs submitted during the first authentication mode and the second authentication mode during the identification or authentication as part of the evaluation of the multiple dimensions.

### Claim 31 (depends on 30)

The method of claim 30, wherein executing the first authentication mode includes accepting the identity token and label inputs during training of one or more first classification neural networks to define the plurality of identification classes.

### Claim 32 (depends on 30)

The method of claim 30, wherein executing one of the first authentication mode or the second authentication mode includes:
determining one or more distances between identity tokens produced, at least in part, by respective generation neural networks;
excluding identity tokens produced by respective generation neural networks having one or more distances exceeding a threshold distance from subsequent training processes; and
including identity tokens having distances within the threshold distance for subsequent training processes.

### Claim 33 (depends on 32)

The method of claim 32, wherein the method comprises determining the authentication mode that includes an enrollment mode for establishing a new entity for subsequent authentication.

### Claim 34 (depends on 21)

The method of claim 21, wherein the at least one processor is configured to trigger at least the second authentication mode responsive to determining a current authentication mode includes the enrollment mode.

### Claim 35 (depends on 33)

The method of claim 33, wherein the method comprises instantiating one or more generation neural networks that comprise at least one learning network configured to accept plain text biometric as input and generate, at least in part, respective identity tokens as output.

### Claim 36 (depends on 33)

The method of claim 33, wherein the method comprises executing one or more first classification neural networks configured to return a label for identification or an unknown result, responsive to input of a respective identity token.

### Claim 37 (depends on 33)

The method of claim 33, wherein the method comprises:
determining a probability of match using the first or second authentication mode is below a threshold value; and
validating an unknown result based on distance analysis of a highest probability match compared to a respective identity token.
