InfosecCampus
← Blog

AI and LLM Security Certifications: Extending the Security Certification Roadmap

3 min read by Sanoop Thomas

Paul Jerimy’s Security Certification Roadmap is the chart many of us send to anyone who asks “which certification should I do next?” It lays out hundreds of credentials by domain, skill level and cost, and it is the reason a lot of people discover that certifications exist beyond the three or four they’ve heard of.

The current version is dated July 2024 and lists 481 certifications. It predates the AI security wave: apart from GIAC’s machine-learning credential (GMLE), none of the credentials in this post are on it. That isn’t a criticism. In mid-2024 there were barely any AI security certifications to list.

That has changed quickly. Eighteen credentials aimed at securing, attacking, governing or auditing AI systems now exist, most of them launched in the last year, from vendors as different as CompTIA, ISACA, OffSec, Hack The Box, GIAC and Practical DevSecOps.

These eighteen are also folded into our Cyber Certs Roadmap, a filterable, continuously-updated page combining Paul Jerimy’s chart with everything we’ve researched beyond it.

The timeline: from nothing to a whole tier

WhenWhat arrived
Aug 2025ISACA introduces AAISM, an AI security management certification
Oct 2025Cloud Security Alliance introduces TAISE
17 Feb 2026CompTIA launches SecAI+
Spring 2026OffSec launches OSAI (AI-300)
2 Apr 2026Hack The Box announces HTB COAE
2026GIAC lists three new AI exams: GAIPS, GOAA, GASAE
Mid 2026Microsoft’s SC-500 Cloud and AI Security Engineer exam reaches general availability

Alongside these sit ISACA’s AAIA (AI audit), IAPP’s AIGP (AI governance), EC-Council’s C|OASP, Practical DevSecOps’ CAISP, CMCPSE and CAASE, Learn Prompting’s AIRTP+, and PECB’s ISO/IEC 42001 implementer and auditor credentials.

What does “AI security certification” even mean?

Before comparing anything, it helps to notice that the phrase covers four different jobs. Many buyers’ regret comes from picking a credential for the wrong one.

  • Securing AI systems. Defending LLM applications, RAG pipelines, model supply chains and AI platforms. Think prompt injection defences, guardrails, data poisoning, AI threat modelling.
  • Attacking AI. AI red teaming: testing LLMs and agentic systems the way an adversary would.
  • Governing and auditing AI. Risk, policy, compliance and audit: NIST AI RMF, ISO/IEC 42001, regulation.
  • AI-assisted security. Using AI to do security work faster: detection, automation, SOC workflows. This is a different skill from securing AI, and some “AI security” courses are really this.

AI Security Roadmap

Securing AI systemsDefend LLM apps, pipelines and platforms
Attacking AIAI red teaming and offensive testing
Governing & auditing AIRisk, compliance, audit, policy
AI-assisted securityUsing AI to do security work
Expert
Securing AI systems
Attacking AI OSAI HTB COAE CAASE
Governing & auditing AI AAISM AAIA
AI-assisted security
Intermediate
Securing AI systems SecAI+ CAISP GAIPS SC-500 CMCPSE
Attacking AI GOAA C|OASP AIRTP+
Governing & auditing AI AIGP ISO 42001 LI ISO 42001 LA
AI-assisted security GASAE
Beginner
Securing AI systems
Attacking AI
Governing & auditing AI TAISE
AI-assisted security
18 credentials · levels and tracks are editorial judgement · hover a chip for the full name

Two things jump out. There is almost nothing at Beginner level, and the offensive and governance tracks are much better served than AI-assisted security, where the credential landscape is still mostly courses rather than certifications.

Other Resources

The resources below are free and covered by almost all of the certification vendors.

#certifications#ai-security#llm#career