# US 2026/0093845 A1 · Privacy-enhancing generation on pre-trained generative models

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

- Number: US 2026/0093845 A1
- Document ID: US20260093845A1
- Status: Published application
- Kind: A1
- Application number: 18/903,651
- Filed: 2024-10-01
- Published: 2026-04-02
- Earliest claimed: 2024-10-01
- Assignees: Robert Bosch GmbH
- Applicants: Robert Bosch GmbH
- Inventors: Bochuan CAO; Sashidhar JAKKAMSETTI; Jorge GUAJARDO MERCHAN
- Web page: https://patentgrep.com/patent/US20260093845A1

## CPC

- G06F 21/6245: {Protecting personal data, e.g. for financial or medical purposes}
- G06F 21/6254: {by anonymising data, e.g. decorrelating personal data from the owner's identification}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Privacy-enhancing interaction with generative models is performed. Private input content is mixed with public input content to create a masked input, the mixing obfuscating the private input content. The masked input is sent to a server generative model for processing to receive a server result. The server result is received from the server generative model. The public input content is processed using a local generative model to generate a local result. The server result and the local result are combined to remove a contribution of the public input content from the server result, thereby resulting in a final output to the private input content.

## Claims

### Claim 1

A method for privacy-enhancing interaction with generative models, comprising:
mixing private input content with public input content to create a masked input, the mixing obfuscating the private input content;
sending the masked input for processing by a server generative model to receive a server result;
receiving the server result from the server generative model;
processing the public input content using a local generative model to generate a local result; and
combining the server result and the local result to remove a contribution of the public input content from the server result, thereby resulting in a final output to the private input content.

### Claim 2 (depends on 1)

The method of claim 1, further comprising appending the final output to the private input content and repeating the mixing, sending, receiving, processing, combining, and appending until an end of output token is reached.

### Claim 3 (depends on 1)

The method of claim 1, wherein the mixing of the private input content with the public input content includes using a hyperparameter a that controls, at a word embedding level, how much weight is given to the private input content versus the public input content.

### Claim 4 (depends on 3)

The method of claim 3, wherein the mixing of the private input content with the public input content includes the addition and/or multiplication, to the output, of noise according to a probability distribution to preclude attempts to reverse the mixing.

### Claim 5 (depends on 4)

The method of claim 4, wherein the noise is distributed according to a Gaussian distribution.

### Claim 6 (depends on 4)

The method of claim 4, wherein the noise is distributed according to a uniform distribution.

### Claim 7 (depends on 1)

The method of claim 1, wherein the server generative model is a model having greater computational ability and greater resource requirements as compared to the local generative model.

### Claim 8 (depends on 1)

The method of claim 1, wherein the combining includes subtracting the local result from the server result utilizing a hyperparameter 3 that adjusts an influence of the local result on the server result.

### Claim 9 (depends on 1)

The method of claim 1, wherein the combining includes performing an argmax operation to utilize token with highest logits.

### Claim 10 (depends on 1)

The method of claim 1, further comprising:
performing the mixing, sending, receiving, processing, and combining a plurality of times with different public input content and the same private input content; and
aggregating the results of the plurality of times to determine the final output, thereby increasing a possibility that tokens with largest logits after the aggregating are related the private input content.

### Claim 11 (depends on 1)

The method of claim 1, wherein the client device is a robot including one or more sensors configured to measure aspects of a condition of a computer-controlled machine and one or more actuators configured to control operation of the computer-controlled machine according to actuator control commands, and further comprising:
receiving the private input content from the one or more sensors; and
controlling the one or more actuators based on the actuator control command determined based on the final output.

### Claim 12

A system for privacy-enhancing inferencing with generative models, comprising:
a client device comprising one or more hardware processors and one or more memories storing a local generative model and a mix algorithm, the client device being configured to execute instructions of the mix algorithm to perform operations including to:
mix private input content with public input content to create a masked input, the mix obfuscating the private input content;
send the masked input for processing by a server generative model to receive a server result;
receive the server result from the server generative model;
process the public input content using the local generative model to generate a local result; and
combine the server result and the local result to remove a contribution of the public input content from the server result, thereby resulting in a final output to the private input content.

### Claim 13 (depends on 12)

The system of claim 12, wherein the client device is further configured to execute the instructions of the mix algorithm to perform operations including to append the final output to the private input content and repeat the mix, send, receive, process, combine, and append until an end of output token is reached.

### Claim 14 (depends on 12)

The system of claim 12, wherein the mix of the private input content with the public input content includes using a hyperparameter a that controls, at a word embedding level, how much weight is given to the private input content versus the public input content.

### Claim 15 (depends on 14)

The system of claim 14, wherein the mix of the private input content with the public input content includes the addition and/or multiplication, to the output, of noise according to a probability distribution to preclude attempts to reverse the mixing.

### Claim 16 (depends on 15)

The system of claim 15, wherein the noise is distributed according to a Gaussian distribution.

### Claim 17 (depends on 15)

The system of claim 15, wherein the noise is distributed according to a uniform distribution.

### Claim 18 (depends on 12)

The system of claim 12, wherein the server generative model is a model having greater computational ability and greater resource requirements as compared to the local generative model.

### Claim 19 (depends on 12)

The system of claim 12, wherein to combine includes to subtract the local result from the server result utilizing a hyperparameter R that adjusts an influence of the local result on the server result.

### Claim 20 (depends on 12)

The system of claim 12, wherein to combine includes to perform an argmax operation to utilize token with highest logits.

### Claim 21 (depends on 12)

The system of claim 12, wherein the client device is further configured to execute the instructions of the mix algorithm to perform operations including to:
perform the mix, send, receive, process, and combine a plurality of times with different public input content and the same private input content; and
aggregate the results of the plurality of times to determine the final output, thereby increasing a possibility that tokens with largest logits after the aggregate are related the private input content.

### Claim 22 (depends on 12)

The system of claim 12, further comprising a generative model service provider comprising one or more hardware processors and one or more memories storing the server generative model in communication over a communications network with the client device.

### Claim 23 (depends on 12)

The system of claim 12, wherein the client device is a robot including one or more sensors configured to measure aspects of a condition of a computer-controlled machine and one or more actuators configured to control operation of the computer-controlled machine according to actuator control commands, and the client device is further configured to:
receive the private input content from the one or more sensors; and
control the one or more actuators based on the actuator control command determined based on the final output.

### Claim 24

A non-transitory computer-readable medium comprising instructions of a mix algorithm that, when executed by one or more hardware processors of a client device, cause the client device to perform operations including to:
mix private input content with public input content to create a masked input, the mix obfuscating the private input content;
send the masked input for processing by a server generative model to receive a server result;
receive the server result from the server generative model;
process the public input content using a local generative model to generate a local result; and
combine the server result and the local result to remove a contribution of the public input content from the server result, thereby resulting in a final output to the private input content.

### Claim 25 (depends on 24)

The non-transitory computer-readable medium of claim 24, further comprising instructions of the mix algorithm that, when executed by the one or more hardware processors of the client device, cause the client device to perform operations including to append the final output to the private input content and repeat the mix, send, receive, process, combine, and append until an end of output token is reached.

### Claim 26 (depends on 24)

The non-transitory computer-readable medium of claim 24, wherein the mix of the private input content with the public input content includes using a hyperparameter a that controls, at a word embedding level, how much weight is given to the private input content versus the public input content.

### Claim 27 (depends on 26)

The non-transitory computer-readable medium of claim 26, wherein the mix of the private input content with the public input content includes the addition and/or multiplication, to the output, of noise according to a probability distribution to preclude attempts to reverse the mixing.

### Claim 28 (depends on 27)

The non-transitory computer-readable medium of claim 27, wherein the noise is distributed according to a Gaussian distribution.

### Claim 29 (depends on 27)

The non-transitory computer-readable medium of claim 27, wherein the noise is distributed according to a uniform distribution.

### Claim 30 (depends on 24)

The non-transitory computer-readable medium of claim 24, wherein to combine includes to subtract the local result from the server result utilizing a hyperparameter 3 that adjusts an influence of the local result on the server result.

### Claim 31 (depends on 24)

The non-transitory computer-readable medium of claim 24, wherein to combine includes to perform an argmax operation to utilize token with highest logits.

### Claim 32 (depends on 24)

The non-transitory computer-readable medium of claim 24, further comprising instructions of the mix algorithm that, when executed by the one or more hardware processors of the client device, cause the client device to perform operations including to:
perform the mix, send, receive, process, and combine a plurality of times with different public input content and the same private input content; and
aggregate the results of the plurality of times to determine the final output, thereby increasing a possibility that tokens with largest logits after the aggregate are related the private input content.

### Claim 33 (depends on 24)

The non-transitory computer-readable medium of claim 24, wherein the client device is a robot including one or more sensors configured to measure aspects of a condition of a computer-controlled machine and one or more actuators configured to control operation of the computer-controlled machine according to actuator control commands, and the non-transitory computer-readable medium further includes instructions of the mix algorithm that, when executed by the one or more hardware processors of the client device, cause the client device to perform operations including to:
receive the private input content from the one or more sensors; and
control the one or more actuators based on the actuator control command determined based on the final output.
