Panel 3 · Planned certificate · 12 weeks
Certificate in Agentic & Protocol-Level Security 1
Agentic & Protocol-Level Security
Core syllabus
What you will investigate
- 01
High-throughput inference with vLLM and SGLang
- 02
KV-cache mechanics, PagedAttention and RadixAttention prefix trees
- 03
Multi-tenant context isolation against indirect prompt injection and memory poisoning
- 04
Static policy prefix caching with pinned compliance rules
Reproducible evidence
Panel deliverable
Build a concurrent serving cluster with tenant KV-cache isolation and pinned policy prefixes. Learner stretch target (not a measured result): greater than 60% reduction in governance-related TTFT overhead.
AI Control Lab deliverable
Deploy a multi-concurrent vLLM/SGLang serving cluster behind the MCML gateway, defeating scripted cross-tenant memory poisoning attacks with a learner stretch target of greater than 60% reduction in governance-related TTFT overhead (not a measured result).
Duration
10 instructional weeks + 2 capstone / defense weeks
Lab
Continuous hands-on work in the AI Control Lab
Assessment
Planned artifact verification and final human sign-off
Stackable by design
Foundational Certificate in AI Assurance & Systems
This panel maps explicitly to the AI Safety & Governance pathway. Panels 1–4 contribute to the 4-panel Foundational milestone; all eight contribute to the 8-panel Advanced Certificate milestone. Certificates can also be pursued individually. Cumulative credentials require the corresponding evidence and human-led defense.
Apply as a StudentUnaccredited institutional credentials; not accredited degrees.