# US 2023/0267200 A1 · A Method of Training a Submodule and Preventing Capture of an AI Module

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

- Number: US 2023/0267200 A1
- Document ID: US20230267200A1
- Status: Published application
- Kind: A1
- Application number: 18/007,249
- Filed: 2021-09-20
- Published: 2023-08-24
- Earliest claimed: 2020-08-06
- Assignees: Robert Bosch GmbH; Robert Bosch Engineering and Business Solutions Private Limited
- Applicants: Robert Bosch GmbH; Robert Bosch Engineering and Business Solutions Private Limited
- Inventors: Mayurbhai Thesia Yash; Manojkumar Somabhai Parmar
- Web page: https://patentgrep.com/patent/US20230267200A1

## CPC

- G06F 21/554: {involving event detection and direct action}
- G06F 21/14: against software analysis or reverse engineering, e.g. by obfuscation
- G06N 20/00: Machine learning
- G06F 2221/033: Test or assess software
- G06N 20/20: Ensemble learning
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method is for training a submodule and preventing capture of an AI module. Input data is received from at least one user through an input interface. The input data is transmitted through a blocker module to an AI module, which computes first output data by executing a first model based on the input data. A submodule in the AI system processes the input data to identify an attack vector from the input data. The submodule executes at least two models in which one model is the first model. Identification information of the attack vector is sent to an information gain module.--

## Claims

### Claim 1

An AI system comprising:
an input interface configured to receive input data from at least one user;
an AI module configured to process the input data and to generate first output data corresponding to the input data;
a blocker module configured to block at least one user, the blocker module further configured to modify the a first output data generated by the AI module;
a submodule configured to identify an attack vector from the input data;
an information gain module configured to calculate an information gain value and to send the information gain value to the blocker module;
a blocker notification module configured to transmit a notification to the an owner of the AI system after detecting the attack vector with the submodule; and
an output interface configured to send an output to the at least one user.

### Claim 2 (depends on 1)

The AI system as claimed in claim 1, wherein the output sent by the output interface comprises the first output data when the submodule does not identify the attack vector from the input data.

### Claim 3

A method of training a submodule in an AI system, the AI system comprising at least an AI module executing a first model, a dataset used to train the AI module, the submodule executing at least two models, the submodule comprising a comparator to compare an the output of the at least two models, the method comprising:
executing the at least two models in the submodule with the dataset; and
recording at least one behavior of the submodule.

### Claim 4 (depends on 3)

The method of training a submodule as claimed in claim 3, wherein the at least two models includesthe first model.

### Claim 5

A method to prevent capturing of an AI module in an AI system, the method comprising:
receiving input data from at least one user through an input interface;
transmitting the input data through a blocker module to an AI module;
computing a first output data by the AI module executing a first model based on the input data;
processing the input data by a submodule to identify an attack vector from the input data, the and
sending identification information of the attack vector to an information gain module.

### Claim 6 (depends on 5)

The method to prevent capturing of an AI module as claimed in claim 5, wherein processing the input data further comprises:
executing at least two models with the input data to generate a first model output and a second model output, wherein the at least two models includes the first model ;
comparing the first and second model outputs ; and
determining the input data as the attack vector based on the comparison.
