AWS clean-rooms documentation change
Summary
Updated headings and clarified documentation about associating custom ML models, including recommendations for using wildcards in allowlists to simplify iteration.
Security assessment
Changes are primarily editorial improvements and workflow recommendations without addressing specific vulnerabilities. While mentioning privacy policies and access controls, these appear to be existing security features rather than new mitigations or vulnerability fixes.
Diff
diff --git a/clean-rooms/latest/userguide/associate-model-algorithm.md b/clean-rooms/latest/userguide/associate-model-algorithm.md index ebfe753de..0d0cbbbda 100644 --- a//clean-rooms/latest/userguide/associate-model-algorithm.md +++ b//clean-rooms/latest/userguide/associate-model-algorithm.md @@ -16 +16 @@ Console -###### To associate a custom ML model algorithm in AWS Clean Rooms +###### To associate a custom ML model algorithm (console) @@ -34 +34,5 @@ API -Associate the configured model algorithm with the collaboration. You also provide a privacy policy that defines who has access to the different logs, allows customers to define regex, and how much data can be exported from the training model outputs or inference results. +To associate a custom ML model algorithm (API) + +Run the following code with your specific parameters. + +You also provide a privacy policy that defines who has access to the different logs, allows customers to define regex, and how much data can be exported from the training model outputs or inference results. @@ -109 +113 @@ After the configured model algorithm is associated to the collaboration, trainin -Because configured model algorithm associations are immutable, we recommend that training data providers who wants to allowlist models for use to use wild cards in `allowedAdditionalAnalyses` during the first few iterations of customm model configuration. This allows model providers to iterate on their code without requiring other training providers to re-associate before training their updated model code with data. +Because configured model algorithm associations are immutable, we recommend that training data providers who wants to allowlist models for use to use wild cards in `allowedAdditionalAnalyses` during the first few iterations of custom model configuration. This allows model providers to iterate on their code without requiring other training providers to re-associate before training their updated model code with data.