# US 2026/0267943 A1 · Machine-learning execution security

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

- Number: US 2026/0267943 A1
- Document ID: US20260267943A1
- Status: Published application
- Kind: A1
- Application number: 19/072,845
- Filed: 2025-03-06
- Published: 2026-09-10
- Earliest claimed: 2025-03-06
- Assignees: Microsoft Technology Licensing, LLC
- Applicants: Microsoft Technology Licensing, LLC
- Inventors: Aditya Vasanth CHALLAPALLY
- Web page: https://patentgrep.com/patent/US20260267943A1

## CPC

- G06F 21/14: against software analysis or reverse engineering, e.g. by obfuscation
- G06F 12/1425: {the protection being physical, e.g. cell, word, block}
- 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

This invention provides a system for enhancing the privacy and security of neural networks through dynamic execution trace obfuscation. The system generates randomized computational patterns to mask the actual processing flow during inference and training, preventing information leakage via side-channel attacks. It employs a randomization engine to reorder operations, vary memory access patterns, and introduce timing variations, ensuring mathematical correctness and model performance. The system includes a protection component for monitoring execution patterns and a performance optimization component to balance security and efficiency.

## Claims

### Claim 1

A method for obfuscating execution of operations of a machine-learning model during execution of inference tasks, the method comprising:
receiving, by a processor, an inference task comprising input data to be processed by the machine-learning model, the inference task received from a requestor;
creating, by the processor, a computational graph mapping execution dependency of the machine-learning model by representing input-dependent operations as nodes and specifying data flow paths between nodes as edges, the computational graph created based on a model architecture of the machine-learning model;
identifying, by the processor, and based upon the computational graph, independent operations within the machine-learning model that are performed during the inference task that can be processed in a different order without changing an output of the inference task;
generating, by the processor, using a pseudo-random number generator, randomization parameters for determining an execution order of the independent operations within the machine-learning model that are performed during the inference task;
ordering, by the processor, the independent operations within the machine-learning model that are performed during the inference task according to the randomization parameters to create a reordered independent operations of the independent operations within the machine-learning model that are performed during the inference task;
executing, by the processor, the reordered independent operations on the input data to produce an output of the inference task, the reordered independent operations generating randomized execution traces for each inference task of the machine-learning model; and
transmitting, by the processor, the output of the inference task to the requestor.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
verifying, by the processor, that the reordered independent operations produces mathematically equivalent results to an original execution order while maintaining random execution sequences.

### Claim 3 (depends on 2)

The method of claim 2, wherein verifying mathematical that the reordered independent operations produces mathematically equivalent results comprises:
comparing output values and intermediate states during execution of the reordered independent operations against reference computations by:
sequentially computing reference values for each layer of the machine-learning model;
calculating numerical differences between reference and actual outputs; and
validating that differences remain within defined tolerance thresholds.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
calculating entropy measurements of execution patterns of the reordered independent operations;
applying pattern recognition algorithms to detect statistical regularities in the execution patterns; and
generating alerts when pattern recognition detects patterns.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
monitoring execution performance metrics during execution of the reordered independent operations;
determining whether the performance metrics indicated performance below a threshold level of performance; and
in response, reducing protection mechanisms by decreasing a randomization frequency.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
partitioning a cache memory into secure and standard regions by:
allocating protected cache lines for security-critical operations; and
designating unprotected cache lines for standard computations;
implementing vector instructions to access the partitioned cache memory by:
loading multiple data components from different cache line offsets simultaneously;
aligning memory accesses to specified-byte array boundaries; and
accessing cache lines through instructions that span multiple regions; and
managing data movement between cache regions by:
scanning arrays at cache-line granularity rather than element-level;
loading security-critical data into protected cache lines; and
serving subsequent reads from processor core's private cache.

### Claim 7 (depends on 1)

The method of claim 1, wherein executing, by the processor, the reordered independent operations on the input data to produce an output of the inference task comprises:
utilizing vector instructions for parallel memory access;
aligning memory accesses to cache-line boundaries; and
performing bulk data transfers at cache-line granularity.

### Claim 8 (depends on 7)

The method of claim 7, wherein utilizing vector instructions comprises:
identifying data elements that can be loaded in parallel;
calculating aligned memory offsets for vector loads; and
executing simultaneous loads across multiple cache lines.

### Claim 9

A computing device for obfuscating execution of operations of a machine-learning model during execution of inference tasks, the computing device comprising:
a hardware processor;
a memory, the memory storing instructions, which when executed by the hardware processor cause the computing device to perform operations comprising:
receiving an inference task comprising input data to be processed by the machine-learning model, the inference task received from a requestor;
creating a computational graph mapping execution dependency of the machine-learning model by representing input-dependent operations as nodes and specifying data flow paths between nodes as edges, the computational graph created based on a model architecture of the machine-learning model;
identifying, based upon the computational graph, independent operations within the machine-learning model that are performed during the inference task that can be processed in a different order without changing an output of the inference task;
generating, using a pseudo-random number generator, randomization parameters for determining an execution order of the independent operations within the machine-learning model that are performed during the inference task;
ordering the independent operations within the machine-learning model that are performed during the inference task according to the randomization parameters to create a reordered independent operations of the independent operations within the machine-learning model that are performed during the inference task;
executing the reordered independent operations on the input data to produce an output of the inference task, the reordered independent operations generating randomized execution traces for each inference task of the machine-learning model; and
transmitting the output of the inference task to the requestor.

### Claim 10 (depends on 9)

The computing device of claim 9, wherein the operations further comprise:
verifying that the reordered execution produces mathematically equivalent results to an original execution order while maintaining random execution sequences.

### Claim 11 (depends on 10)

The computing device of claim 10, wherein the operation of verifying that the reordered execution produces mathematically equivalent results comprises:
comparing output values and intermediate states during execution of the reordered independent operations against reference computations by:
sequentially computing reference values for each layer of the machine-learning model;
calculating numerical differences between reference and actual outputs; and
validating that differences remain within defined tolerance thresholds.

### Claim 12 (depends on 9)

The computing device of claim 9, wherein the operations further comprise:
calculating entropy measurements of execution patterns of the reordered independent operations;
applying pattern recognition algorithms to detect statistical regularities in the execution patterns; and
generating alerts when pattern recognition detects patterns.

### Claim 13 (depends on 9)

The computing device of claim 9, wherein the operations further comprise:
monitoring execution performance metrics during execution of the reordered independent operations;
determining whether the performance metrics indicated performance below a threshold level of performance; and
in response, reducing protection mechanisms by decreasing a randomization frequency.

### Claim 14 (depends on 9)

The computing device of claim 9, wherein the operations further comprise:
partitioning a cache memory into secure and standard regions by:
allocating protected cache lines for security-critical operations; and
designating unprotected cache lines for standard computations;
implementing vector instructions to access the partitioned cache memory by:
loading multiple data components from different cache line offsets simultaneously;
aligning memory accesses to specified-byte array boundaries; and
accessing cache lines through instructions that span multiple regions; and
managing data movement between cache regions by:
scanning arrays at cache-line granularity rather than element-level;
loading security-critical data into protected cache lines; and
serving subsequent reads from processor core's private cache.

### Claim 15 (depends on 9)

The computing device of claim 9, wherein the operation of executing the reordered independent operations on the input data to produce an output of the inference task comprises:
utilizing vector instructions for parallel memory access;
aligning memory accesses to cache-line boundaries; and
performing bulk data transfers at cache-line granularity.

### Claim 16 (depends on 15)

The computing device of claim 15, wherein the operation of utilizing vector instructions comprises:
identifying data elements that can be loaded in parallel;
calculating aligned memory offsets for vector loads; and
executing simultaneous loads across multiple cache lines.

### Claim 17

A non-transitory machine-readable medium, storing instructions for obfuscating execution of operations of a machine-learning model during execution of inference tasks, the instructions, which when executed, cause the machine to perform operations comprising:
receiving an inference task comprising input data to be processed by the machine-learning model, the inference task received from a requestor;
creating a computational graph mapping execution dependency of the machine-learning model by representing input-dependent operations as nodes and specifying data flow paths between nodes as edges, the computational graph created based on a model architecture of the machine-learning model;
identifying, based upon the computational graph, independent operations within the machine-learning model that are performed during the inference task that can be processed in a different order without changing an output of the inference task;
generating, using a pseudo-random number generator, randomization parameters for determining an execution order of the independent operations within the machine-learning model that are performed during the inference task;
ordering the independent operations within the machine-learning model that are performed during the inference task according to the randomization parameters to create a reordered independent operations of the independent operations within the machine-learning model that are performed during the inference task;
executing the reordered independent operations on the input data to produce an output of the inference task, the reordered independent operations generating randomized execution traces for each inference task of the machine-learning model; and
transmitting the output of the inference task to the requestor.

### Claim 18 (depends on 17)

The non-transitory machine-readable medium of claim 17, wherein the operations further comprise:
verifying that the reordered execution produces mathematically equivalent results to an original execution order while maintaining random execution sequences.

### Claim 19 (depends on 18)

The non-transitory machine-readable medium of claim 18, wherein the operation of verifying that the reordered execution produces mathematically equivalent results comprises:
comparing output values and intermediate states during execution of the reordered independent operations against reference computations by:
sequentially computing reference values for each layer of the machine-learning model;
calculating numerical differences between reference and actual outputs; and
validating that differences remain within defined tolerance thresholds.

### Claim 20 (depends on 17)

The non-transitory machine-readable medium of claim 17, wherein the operations further comprise:
calculating entropy measurements of execution patterns of the reordered independent operations;
applying pattern recognition algorithms to detect statistical regularities in the execution patterns; and
generating alerts when pattern recognition detects patterns.
