Workshop checks passed0 / 3
Protecting ML Data and Artifacts
A relevant document may belong to another customer, an anonymous statistic may still expose someone's contribution, and a model file may execute code when loaded. Put the checks around those concrete effects and make clear what each check can establish.
Boundaries around learning systems
A useful record may be private, and a downloaded model may execute code when loaded. We’ll examine each operation before deciding what the application can safely permit.
- 01Ready to exploreRelevant Evidence Is Not Necessarily Permitted Evidence
Filter retrieval candidates by trusted authority before ranking what the agent may read.
- 02Ready to exploreHow Much Could One Person Change This Statistic?
Derive bounded-mean sensitivity before discussing noise and privacy accounting.
- 03Ready to exploreA Model File Is Part of the Software Supply Chain
Verify bytes against trusted provenance and choose a constrained loading format before using a downloaded model.