OC-MIDPASD · AI Security: DefensivePractitionerIn development
Model Integrity & Data Poisoning Defense
In development · enrolment sequence to be confirmed
LevelPractitioner
PrerequisitesFoundation or equivalent
StatusIn development
SpecificationDraft · not approved
EnrolmentNot yet open
01Overview
Model provenance verification, poisoning detection and integrity validation controls.
Domain scope · ASD
The defensive core: AI threat taxonomy, control-plane implementation, token security, pipeline and model integrity, and AI incident response.
Intended for: Security practitioners moving into AI security or deepening it
02Proposed case references
Source review pendingI-2
OpenAI/DeepSeek Model Distillation CampaignSource review · In review
Proposed connection, subject to source review. I-2 is the anchor case. Model provenance and integrity controls are taught against its documented distillation pattern.
03Assessment
Format, duration, passing score and practical component are published with the approved specification.
04Instructor
TBA
Announced when appointed
Instructors are practitioners appointed against a written standard for the ASD domain.
Official specification registerOC-MIDPSpecification not yet issued
Version —Last reviewed —
This course is in active development. Duration, pricing, session dates and instructor are published when confirmed. Proposed case references, framework references, syllabus, labs and assessment are drafts until the course specification is approved.