Overview
The AI Safety, Trust & Responsibility (AISTR) Certification is WDTA's core professional credential for AI practitioners. Built on the global AI STR framework initiated by WDTA — spanning research, standards, evaluation and certification — it covers safety risk identification, trustworthiness verification, foundations of adversarial and red-team testing, and the principles of responsible AI governance.
On completion you will be able to independently conduct AI safety evaluations, issue assessment conclusions and contribute to governance decisions in real business settings — and receive a verifiable WDTA credential and digital badge.
Who It's For
Run pre-deployment safety evaluation and risk control.
Want a systematic grasp of trustworthy-AI methods.
Establish safety and compliance baselines for products.
Enter the AI safety field with an authoritative credential.
What You'll Be Able to Do
- ✓Identify safety risks across data, model and deployment stages and build a risk inventory.
- ✓Verify model trustworthiness, robustness and fairness using standardized methods.
- ✓Design and run foundational adversarial and red-team evaluation processes.
- ✓Produce assessment reports and governance recommendations aligned to responsible-AI principles.
Exam Syllabus
Overview of the AI STR framework, core terminology, global standards and regulatory trends — building a holistic view of trustworthy AI.
Risk identification, threat modeling and grading across the data, training, inference and deployment lifecycle.
Robustness testing, fairness metrics, explainability methods and the verification metric system.
Common attack vectors, adversarial examples, prompt-injection basics and red-team process design.
Responsible-AI principles, governance frameworks, assessment-report writing and organizational rollout.
Assessment
Credential You Earn
On passing you receive a uniquely numbered, online-verifiable e-certificate and digital badge — shareable to LinkedIn and your résumé, and recorded in the WDTA Learning Passport.
