eIQ® Model Watermarking Technology

EIQ-WATERM-TECH

Collecting data and training ML models are substantial investments and data ownership is a differentiator. However, a copyist can typically copy or clone a model with little effort. Besides extracting a model from a device via a memory dump, attacks have been published showing that to clone a model, access to the input-output behavior of the ML algorithm already suffices. Furthermore, copyright and patent laws are not applicable directly to most ML model IP.

To help developers in adding a piece of copyright-protected information to an ML model as to strengthen the copyright claim, and to provide a means to prove unauthorized copying, NXP has developed a method for embedding a watermark in a model. This feature is available within the eIQ Toolkit ML Software Enablement environment.

Software Details

Features

  • Enhances the copyright protection to an ML model
  • Generates reports and artifacts and instructions needed to prove model ownership
  • No additional overhead to model performance or reduction in accuracy
  • Model Protection through Watermarking
    • Owning data is a differentiator to companies in the ML space
    • Collecting data and training a model is a substantial investment
    • Model watermarking protects your model intellectual property in the event it gets copied or stolen
  • Working Principles
    • The tool overlays a secret drawing on objects from a selected base class during training and labels these overlays as target class
    • When presented with base-class objects overlaid with the secret drawing during runtime the model will predict the target class instead of the base class hence identifying that the original model was copied

Supported Devices

  • i.MX8: i.MX 8 Family – Arm® Cortex®-A53, Cortex-A72, Virtualization, Vision, 3D Graphics, 4K Video
  • i.MX8M: i.MX 8M Family - Arm® Cortex®-A53, Cortex-M4, Audio, Voice, Video
  • i.MX8MMINI: i.MX 8M Mini - Arm® Cortex®-A53, Cortex-M4, Audio, Voice, Video
  • i.MX8MNANO: i.MX 8M Nano Family - Arm® Cortex®-A53, Cortex-M7
  • IMX8MPLUS: i.MX 8M Plus – Arm® Cortex®-A53, Machine Learning, Vision, Multimedia and Industrial IoT
  • i.MX8X: i.MX 8X Family – Arm® Cortex®-A35, 3D Graphics, 4K Video, DSP, Error Correcting Code on DDR
  • i.MX93: i.MX 93 Applications Processor Family – Arm® Cortex®-A55, ML Acceleration, Power Efficient MPU
  • iMX95: i.MX 95 Applications Processor Family: High-Performance, Safety Enabled Platform with eIQ® Neutron NPU
  • i.MX-RT500: i.MX RT500 Crossover MCU with Arm® Cortex®-M33, DSP and GPU Cores
  • i.MX-RT600: i.MX RT600 Crossover MCU with Arm® Cortex®-M33 and DSP Cores
  • i.MX-RT1050: i.MX RT1050 Crossover MCU with Arm® Cortex®-M7 Core
  • i.MX-RT1060: i.MX RT1060: Crossover MCU with Arm® Cortex®-M7
  • i.MX-RT1064: i.MX RT1064: Crossover MCU with Arm® Cortex®-M7
  • i.MX-RT1160: i.MX RT1160 Crossover MCU Dual-Core Arm® Cortex®-M7 and Cortex-M4
  • i.MX-RT1170: i.MX RT1170: 1 GHz Crossover MCU with Arm® Cortex® Cores

Downloads

Quick reference to our software types.
Filters

1 download

Note: For better experience, software downloads are recommended on desktop.

Y true 0 SSPEIQ-WATERM-TECHen 1 White Paper White Paper t530 1 en_US en_US en White Paper White Paper 1 1 1 Japanese 製造業者やサプライヤーが、運用上重要な機器について顧客に保守契約を提供することは一般的です。顧客のビジネスに影響を与える可能性のある障害を回避するために、機械学習 (ML) モデルに基づく予防保守アプリケーションが使用されます。 1674496111743713159237ja SSP 24.7 MB None None documents None 1674496111743713159237 /docs/ja/white-paper/IPMLWP.pdf 24700965 /docs/ja/white-paper/IPMLWP.pdf IPMLWP documents N N 2023-01-23 Intellectual Property Aspects of Machine Learning /docs/ja/white-paper/IPMLWP.pdf /docs/ja/white-paper/IPMLWP.pdf White Paper N 918633085541740938 2025-03-08 ja Jul 13, 2023 918633085541740938 White Paper Y N 機械学習における知的財産権の問題 1 English It is common for manufacturers and suppliers to offer maintenance contracts to their customers for operation-critical equipment. To help avoid failures that could impact the customer’s business, a preventative maintenance application based on a Machine Learning (ML) Model is used. 1674496111743713159237 SSP 24.7 MB None None documents None 1674496111743713159237 /docs/en/white-paper/IPMLWP.pdf 24700965 /docs/en/white-paper/IPMLWP.pdf IPMLWP documents N N 2023-01-23 Intellectual Property Aspects of Machine Learning /docs/en/white-paper/IPMLWP.pdf /docs/en/white-paper/IPMLWP.pdf White Paper N 918633085541740938 2025-03-08 pdf N en Jul 13, 2023 918633085541740938 White Paper Y N Intellectual Property Aspects of Machine Learning false 0 EIQ-WATERM-TECH downloads en true 1 Y SSP White Paper 1 /docs/en/white-paper/IPMLWP.pdf 2023-01-23 1674496111743713159237 SSP 1 Jul 13, 2023 White Paper It is common for manufacturers and suppliers to offer maintenance contracts to their customers for operation-critical equipment. To help avoid failures that could impact the customer’s business, a preventative maintenance application based on a Machine Learning (ML) Model is used. None /docs/en/white-paper/IPMLWP.pdf English documents 24700965 None 918633085541740938 2025-03-08 N /docs/en/white-paper/IPMLWP.pdf Intellectual Property Aspects of Machine Learning /docs/en/white-paper/IPMLWP.pdf documents 918633085541740938 White Paper N en None Y pdf 1 N N Intellectual Property Aspects of Machine Learning 24.7 MB IPMLWP N 1674496111743713159237 true Y Softwares

Documentation

Quick reference to our documentation types.

Filters

1 documents

Compact List

Training

Filters

1 trainings

Support

What do you need help with?

  • Narrow your search
Search