ProfessionalVendor-neutralOffSec· issued from US

OSAI

OffSec AI Security Practitioner

Offensive AI security — adversarial ML, LLM attacks, agent abuse.

Exam fee
$1,499
Ongoing
$0/yr AMF · 30 CPE/yr
Study time
250–400 hrs
Delivery
Hands-on practical lab
Validity
3 yrs (renewal cycle)

› Quality score

23.5 / 40

Four-axis SecProve rubric, each 0–10. SecProve editorial assessment — each axis carries a written justification so you can push back on any single call without dismissing the whole score.

Blueprint rigor
How well-defined and rigorous the exam blueprint is.
Public syllabus but content is still emerging — adversarial-ML methodology hasn't settled.
6.5/10
Practical evidence
Hands-on labs / written reports vs pure MCQ.
Hands-on lab against a simulated AI/ML deployment. Practice rigour is genuine if narrow.
9.0/10
Currency & upkeep
How aggressively content is kept current with the field.
OffSec is updating quickly to follow the field; baseline content still maturing.
5.0/10
Market recognition
How often this signal actually moves a hiring decision.
Brand-new credential (2025); recognition is forming. Early-adopter signal only.
3.0/10

› Built for these roles

AI Red TeamerML Security Engineer (offensive)Adversarial-ML Researcher

› Exam format

Hands-on lab exam against a simulated AI/ML deployment — adversarial perturbations, prompt-injection chains, agent abuse. Online proctored. New credential as of 2025.

Passing score
Pass/fail across practical AI-attack scenarios
Retake policy
Fee: $249 per attempt
Wait: 0d between attempts

Retake voucher $249 separately. No wait period beyond exam scheduling availability.

› Recertification

90 OffSec CE credits over the three-year cycle (avg 30/yr). No annual maintenance fee.

› NICE Framework work roles

The NIST NICE work-role IDs this cert maps to. NICCS lookup.

PD-WRL-007PD-WRL-002
Recognition
GlobalUS
Exam languages
en

› Core domains covered

The 4 domains this cert is centrally about. Passing the exam demonstrates working knowledge of each.

› Also touched

Present in the blueprint but not the primary focus — you’ll be introduced but shouldn’t expect depth.

› Prerequisites

Experience

Strong offensive security background (OSCP-level). Python fluency required; ML familiarity strongly recommended.

Knowledge assumed
  • Adversarial ML attack taxonomy
  • LLM prompt injection and jailbreak techniques
  • Agent abuse and tool-use exploitation

› Progression

requiredrecommended

Where this cert fits in the typical learning path. Required edges are vendor-gated; recommended edges reflect de facto industry progression.

Required prereqs (0)

No vendor-gated prereqs.

Recommended priors (1)
OSAI
OffSec
Required by (0)

No certs require this one.

Recommended next (0)

No follow-on certs reference this one yet.

› Study materials

Curated starting points. Not exhaustive — vet each against your learning style and the current exam version.

› Version & lifecycle

Current version
Launched 2024
Released
2024-09

Newest OffSec credential focused on AI/ML attack tradecraft.

› Salary signal

AI red team / offensive AI engineer, US, 4-6 years. New role category.

$130K$200K
median $160K

Robert Half Salary Guide extrapolation · 2024 · US base only · p25–p75 range

› How it compares

vs
GASAE

OffSec OSAI is hands-on AI attack tradecraft; GASAE is automation-engineering focused.

↔ Compare side-by-side

› Careers that commonly pursue this cert

AI Security Engineer

Secure AI/ML systems from adversarial attacks, data poisoning, and model compromise. The fastest-growing specialization in cybersecurity.

ML Platform Security Engineer

Secures the platform that trains, stores, and serves ML models — multi-tenant GPU isolation, pipeline integrity, feature-store hygiene, secrets management in ML workflows.

See this cert’s domains highlighted on the interactive map, or compare it against the rest of the catalog.