A working method for securing the automated pipeline that takes a machine learning model from raw training data to a running production service. You will treat each pipeline stage, data ingestion, training, evaluation, registry, and deployment, as a distinct attack surface, verify training data provenance to catch a compromise that never touches a single line of code, apply the same integrity requirements already expected of any software artifact repository to a model registry, extend the least-privilege pipeline principle from CI/CD Pipeline Hardening to a model pipeline's own stages, and build the versioning, rollback, and monitoring practices needed for when prevention, as it eventually will, falls short. Broader frontier artificial intelligence supply chain concerns are cross-referenced rather than repeated.
Nothing. Every course, exam, and certificate on the catalog is free — including retakes. All you need is a free Safeguard account.
None. The flagship course, Safeguard Certified Practitioner, is a beginner-level course — basic familiarity with how software is built helps, but every exam question is answerable from the lessons themselves.
You can retake it after a 24-hour cooldown, as many times as you need. Retakes are free, and each attempt draws a fresh random set of questions.
The Safeguard Certified Practitioner credential is valid for 24 months from issue. The expiry date is printed on the certificate and shown live on its public verification page. Renewing means passing the current exam again.
