General

Runtime Safeguards

Techniques that watch a running system and limit, reroute or stop it when it leaves expected bounds.

2 techniques

2 techniques
GoalsModelsData TypesDescription
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...
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...
Rows per page
Page 1 of 1