UI/UX Safety and Controls
Checklist / Questions to ask your team
Do you have a mitigation plan for ML harm situations (ie. ystem that was designed and deployed for that task produced harmful and unexpected results) especially common with use of deep reinforcement and unsupervised learning, agents acting in broader environment settings.
Did you design to enable humans can step in and remedy if needed
How did you design not to make moves with very bad repercussions?
What happens if model has no training data for a specific scenario
Do you ensure privacy best practices when applying machine learning to sensitive data eg. medical data?
2, Tools
to shield from adversarial attacks the IBM Adversarial Robustness 360
toolbox3. Use Cases
4. Related Information
Case Studies
4. Further Readings