Introduction
Engineering AI you can trust
()
Why does trust engineering matter?
()
1. Foundations of Trust Engineering
What is trust in AI engineering?
()
Trust engineering in practice
()
2. AI Risk Basics
PR nightmares
()
AI risks part 1: Algorithmic challenges
()
AI risks part 2: Human challenges
()
Context and hallucinations
()
Tracing information sources
()
Adversarial examples
()
3. Understanding AI Incidents
Introducing the AI incident database
()
AI risk taxonomies
()
When business incentives conflict with trust
()
4. Human-AI Collaboration
Balancing humans and machines
()
Explainability and decision-making
()
Decision design in the enterprise
()
Context and roles
()
Managing expectations
()
Minimizing scope and thoughtful friction
()
Rebalance a human-AI workflow to de-risk
()
5. Transparency and Accountability
Understanding model evaluation
()
Understanding model limitations
()
Exploring model cards and equivalents
()
Traceability
()
Designing response plans
()
A survey of trust infrastructure
()
AI risk assessments
()
AI assurance and audits
()
6. Building Your Toolkit
Applied trust engineering
()
7. Next Steps
Keep up with trust
()
Ex_Files_Trust_Engineering_AI.zip
(907 KB)