C4 · AI Security Engineering (core)
AI Deployment and Supply-Chain Security
Protect deployment environments, model and software artifacts, credentials, and promotion pipelines.
Proposed
0 of 6 modules accessible. Joining Skool does not unlock planned modules.
At a glance
- Audience
- Security practitioners taking responsibility for AI systems.
- Prerequisites
- C1–C3
- One cloud platform
- CI/CD, containers, and infrastructure-as-code basics
- Planned duration
- 20 hours. On one reference deployment stack. Assumes the entry requirements are met. Planning estimate, not a measured completion time. Per module: 2 to 4 hours, plus practice.
- Assessment
- Exposure, identity, integrity and rollback tests with rubric.
- What is free
- The free foundation module listed on each course page, as it releases, plus community access.
Job tasks this course prepares you for
- Review deployment architecture
- Constrain serving access
- Verify artifacts
- Enforce controlled promotion and rollback
Learning outcomes
- Deploy the reference service with no embedded credentials and no unintended public administrative access.
- Reject an altered or unapproved model or package artifact in the pipeline.
- Enforce separation between build, evaluation, approval, and deployment identities.
- Roll back to an approved configuration and document the remaining lifecycle dependencies.
Modules
00Deployment patternsProposed
Topics
- managed model API versus self-hosted inference; who owns which control.
01Serving and infrastructureProposed
Topics
- ingress, authentication, private connectivity, egress, tenant isolation, secrets.
02Software and model supply chainProposed
Topics
- dependencies, registries, artifact integrity, unsafe model loading, limits of provenance.
03Lifecycle interfacesProposed
Topics
- datasets, fine-tuning jobs, experiment tracking, model registry, promotion permissions.
04Pipeline enforcementProposed
Topics
- approved artifacts, least-privilege jobs, evaluation evidence, rollback.
05Operational resilienceProposed
Topics
- quotas, cost limits, availability, provider failure, version change.
Labs and deliverables
- Harden a supplied deployment and CI pipeline. Infrastructure changes, artifact policy, promotion evidence, and rollback record.
Labs run on SIFT, the forensics workstation Rob T. Lee created, on your own machine. Each module states what it needs before you start. Each module confirms its setup requirements and any cloud or API costs before it opens. About the SIFT lab environment.
Assessment
Exposure, identity, integrity and rollback tests with rubric. A named assessor grades against the published rubric (rubric to be published before release).
Pass criteria
- All designated exposure, identity, and artifact-integrity tests pass
- Rollback succeeds
- 80% rubric
Critical failures
- Unauthorized cross-tenant access
- Out-of-scope activity
- Uncontrolled destructive action
- Fabricated evidence
- Exposed credentials
What this course does not teach
- No full Kubernetes administration, GPU or hardware security, or comprehensive adversarial ML (see E1).