Publications
Machine learning model signatures
Abstract
A system and techniques for configuring a trained model to dedicate a portion of its output data to include signature data that may be used to identify information about the model. The model may be configured so that some portion of its least-significant output bits may represent the signature data. The signature data may be a unique code that corresponds to the particular model. The signature data may also include encoded data that may represent information such as a model version, model author, or the like. A recipient of the model output data may thus use the signature data to determine information about the particular model, even if the model itself is inaccessible.
- Date
- 2026
- Authors
- Y Wu, P Natarajan, RM Reddy, P Natarajan, X Zhang
- Inventors
- Yue Wu, Pradeep Natarajan, Rajiv M Reddy, Premkumar Natarajan, Xu Zhang
- Patent_office
- US
- Patent_number
- 12530189
- Application_number
- 17854484