AWS Clean Rooms ML now supports redacted error log summaries

AWS Clean Rooms ML custom modeling enables you and your partners to train and run inference on a custom ML models using collective datasets at scale without having to share your sensitive data or intellectual property. With today’s launch, collaborators can configure a new privacy control that sends redacted error log summaries to specified collaboration members. Error log summaries include the exception type, error message, and line in the code where the error occurred. When associating the model to the collaboration, collaborators can decide and agree which members will receive error log summaries and whether those summaries will contain detectable Personally Identifiable Information (PII), numbers, or custom strings redacted.

AWS Clean Rooms ML helps you and your partners apply privacy-enhancing controls to safeguard your proprietary data and ML models while generating predictive insights—all without sharing or copying one another’s raw data or models. For more information about the AWS Regions where AWS Clean Rooms ML is available, see the AWS Regions table. To learn more, visit AWS Clean Rooms ML.