Safety
Monitoring
Techniques that watch a running system's inputs and usage and flag what is unusual, out of scope or misused.
5 techniques
5 techniques
| Goals | Models | Data Types | Description | |||
|---|---|---|---|---|---|---|
| Out-of-Distribution Detector for Neural Networks | Algorithmic | Architecture/neural Networks Paradigm/discriminative +3 | Image | ODIN (Out-of-Distribution Detector for Neural Networks) flags inputs that look unlike the data a neural network... | ||
| Runtime Monitoring and Circuit Breakers | Algorithmic | Architecture/model Agnostic Requirements/black Box | Any | Runtime monitoring and circuit breakers observe a deployed AI service and restrict model calls when configured signals... | ||
| API Usage Pattern Monitoring | Algorithmic | Architecture/model Agnostic Requirements/black Box | Any | API usage pattern monitoring examines how each account uses a deployed model's API, to catch misuse that no single... | ||
| Out-of-Domain Detection | Algorithmic | Architecture/model Agnostic Architecture/neural Networks/transformer/llm +2 | Text | Out-of-domain detection checks whether a user's query falls inside the topics and tasks a conversational AI system is... | ||
| Signal Temporal Logic Monitoring | Algorithmic | Architecture/model Agnostic Requirements/black Box | Time-series | Signal temporal logic (STL) monitoring checks the signals a system produces over time, such as speeds, distances,... |
Rows per page
Page 1 of 1