Model Watermarking

Intermediate

Embedding signals to prove model ownership.

Full Definition

Embedding signals to prove model ownership.

Keywords

IP protection

Domains

AI Economics & Strategy

Related Terms

Canary Tokens related to

Detecting unauthorized model outputs or data leaks.

 Compute Scaling related to

Increasing model capacity via compute.

 Data Scaling related to

Increasing performance via more data.

 Chinchilla Scaling related to

Scaling law optimizing compute vs data.

 Gradient Leakage related to

Recovering training data from gradients.

 Model Inversion related to

Inferring sensitive features of training data.

 Prompt Leakage related to

Extracting system prompts or hidden instructions.

 Supply Chain Attack related to

Compromising AI systems via libraries, models, or datasets.

Concept Map

See how Model Watermarking connects to other concepts.

Open Knowledge Graph