COASP
Certified Offensive AI Security Professional
EC-Council certification for offensive AI security. Focus on Prompt Injection, Model Extraction, Training Data Poisoning, Agent Hijacking, LLM Jailbreaking. Aligned with OWASP LLM Top 10, NIST AI RMF, ISO 42001. Brand new since February 2026.
› Quality score
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.
› Built for these roles
› Exam format
Details pending
First retake immediate; 14 days between attempts 2-3, 1 month between 3-4, 3 months between 4-5. Max 5 attempts/year.
› Recertification
ECE Credits
› 3-year cost of ownership
Excludes study materials, training, retake risk, and lost-wage opportunity. Use as a floor estimate.
› NICE Framework work roles
The NIST NICE work-role IDs this cert maps to. NICCS lookup.
› Core domains covered
The 2 domains this cert is centrally about. Passing the exam demonstrates working knowledge of each.
Evasion attacks, poisoning attacks, model extraction, membership inference, model inversion, gradient-based attacks.
Prompt injection (direct & indirect), jailbreaking, prompt leaking, training data extraction, hallucination exploitation, agent manipulation.
› Prerequisites
Not specified
› Careers that commonly pursue this cert
Secure AI/ML systems from adversarial attacks, data poisoning, and model compromise. The fastest-growing specialization in cybersecurity.
See this cert’s domains highlighted on the interactive map, or compare it against the rest of the catalog.