At Microsoft, we approach security for AI systems holistically using a full stack red teaming that goes beyond just testing an AI model.
Corporate Vice President of red teaming at Microsoft Craig Nelson describes what he looks for with this method, “I’m interested in the model, but I’m also interested in how that model connects with underlying additional data. And then how that model also executes automation from the back end.”
In this video, Nelson explains why securing AI requires more than testing the model alone.
Key takeaways
When you apply full stack red teaming to AI, here are some key questions to answer:
- How are AI models connecting to data sources?
- What backend automation do we allow AI to execute?
- What security credentials do we require?
- Do we have logs you need to understand how the model works with our backend infrastructure?
Related links
- Read about our open automation framework for red teaming generative AI systems.
- Explore our AI red teaming 101 training series.
- Get an overview of security and governance features available for Azure Machine Learning.
- Find out how to safeguard your organization’s AI based on our experience at Microsoft.
