Safety
Safeguards
Techniques that lower the chance or impact of harm, such as redundancy, data screening, human oversight or documented limits of use.
5 techniques
5 techniques
| Goals | Models | Data Types | Description | |||
|---|---|---|---|---|---|---|
| Human-in-the-Loop Safeguards | Process | Architecture/model Agnostic Requirements/black Box | Any | Human-in-the-loop safeguards hold an AI system's output at a checkpoint until a trained person has reviewed it.... | ||
| Confidence Thresholding | Algorithmic | Architecture/model Agnostic Requirements/black Box +1 | Any | Confidence thresholding uses a model score to decide whether a prediction should proceed automatically or receive... | ||
| Model Cards | Documentation | Architecture/model Agnostic Requirements/black Box | Any | A model card is a short structured document published with a trained model, stating what the model is for and what it... | ||
| Datasheets for Datasets | Documentation | Architecture/model Agnostic Requirements/black Box | Any | A datasheet for a dataset is a short document that accompanies the dataset and answers a set of questions about it, in... | ||
| Data Poisoning Detection | Algorithmic | Architecture/model Agnostic Requirements/white Box +1 | Any | Data poisoning detection looks for training examples that an attacker has planted to change how a model behaves. The... |
Rows per page
Page 1 of 1