Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Method for protecting the intellectual property rights of a trained machine learning network model using digital watermarking by adding, on purpose, an anomaly to the training data

Method for protecting the intellectual property rights of a trained machine learning network model using digital watermarking by adding, on purpose, an anomaly to the training data

US Patent 11461577 · Granted Oct 4, 2022

Assignee

No assignee recorded.

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Method for categorizing a scene comprising a sub-scene with machine learning2024
Medical device for transcription of appearances in an image to text with machine2024
Method for adapting the quality and/or frame rate of a live video stream based u2024
Method and system for automatically annotating and identifying a living being or2024
System to notify a request for help by detecting an intent to press a button, sa2024
Monitoring and analyzing body language with machine learning, using artificial i2024
Medical device for transcription of appearances in an image to text with machine2023
Method for categorizing a scene comprising a sub-scene with machine learning2023
Monitoring and analyzing body language with machine learning, using artificial i2022
Method and system for automatically annotating and identifying a living being or2022
Determining a social group to which customers belong from appearance and using a2021
Method for categorizing a scene comprising a sub-scene with machine learning2020