Control Model Execution with Obfuscated Operating Data

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing control models for technical systems face challenges in maintaining confidentiality of internal workings and critical data, as they often require sharing sensitive information between vendors and users, leading to potential compromise of encryption and loss of confidentiality.

Innovation Solution

A method involving a transformation function that reduces and obfuscates operating data, separating access domains to prevent direct access and reconstruction of original data, allowing for secure control model execution without needing encryption, where the transformation function and control model are generated and executed in distinct access domains.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the control model is provided in encrypted form with an interpreter for decryption at run time, then the confidentiality of the control model is improved, but the user can decompile the interpreter and compromise the encryption

Engineering Contradiction:

Improveconfidentiality of control modelVSAvoidcomplexity of encryption and interpreter system

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent extracts the confidential control model from the execution environment by providing only input-output interfaces. The control model is taken out as a black box that processes transformed data without exposing its internal structure, weights, or architecture to the user system.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent introduces a transformation function as an intermediary that converts input data into transformed data before it reaches the control model. This intermediary layer prevents direct access to the control model's internal workings while still enabling functional operation.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Adaptability or versatility

If the vendor provides the control model to the user, then the control functionality is improved, but the internal workings of the control model become accessible and may be compromised

Engineering Contradiction:

Improvecontrol functionalityVSAvoidconfidentiality of control model

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The patent segments the control system into distinct components: the transformation function, the control model, and the execution environment. The control model is provided as a separate, isolated component that receives transformed data and produces control outputs without exposing its internal structure.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent creates a functional copy of the control model's behavior through the transformation function, which processes data in a way that produces the same control outputs as the original model would, without requiring the user to have access to the actual model parameters or structure.

Inventive Principle:

Principle #26Copying

3Measurement precision

If the user provides operating data to the vendor for control model training, then the control model accuracy is improved, but the confidentiality of the user's critical data is compromised

Engineering Contradiction:

Improvecontrol model accuracyVSAvoidconfidentiality of operating data

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The patent inverts the traditional data flow by having the transformation function (provided by the vendor) process the user's data locally before any transmission. Instead of sending raw data to the vendor for processing, the user's data is transformed in-place, and only the transformed results are used for control model operation.

Inventive Principle:

Principle #13The other way round (Inversion)

Solution Approach 2:

The patent changes the state of the operating data through the transformation function, which applies mathematical transformations to convert the original data into a different representation. This parameter transformation maintains the functional relationship needed for control while fundamentally altering the data's form and protecting its confidentiality.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS11567461B2Method and device for controlling a technical system using a control model

Publication Date: 2023.01.31 SIEMENS AG

AI summary

In order to control a technical system using a control model, a transformation function is provided for reducing and/or obfuscating operating data of the technical system so as to obtain transformed operating data. In addition, the control model is generated by a model generator according to a first set of operating data of the technical system. In an access domain separated from the control model, a second set of operating data of the technical system is recorded and transformed by the transformation function into a transformed second set of operating data which is received by a model execution system. The control model is then executed by the model execution system, by supplying the transformed second set of operating data in an access domain separated from the second set of operating data, control data being derived from the transformed second set of operating data.