ISO/IEC 27090 is new international guidance on security threats that are specific to AI: poisoned data, hidden instructions, stolen models and leaking information. It isn’t something you get certified against. It’s a checklist that works with what you already have, such as ISO 27001 or ISO 42001.
Ordinary security still matters, but AI adds new ways in. ISO 27090 names them and sets out how to address them across the AI life cycle, from data to retirement.
The information security management system many organisations already have. Certifiable.
How you govern AI across the organisation: roles, risk, impact and oversight. Certifiable.
The AI-specific threats and controls that plug into both. Guidance, not certifiable, so you use it as a checklist.
Know what an assistant can reach and what a hidden instruction could make it do, before you connect it to your inbox.
Customers now ask how you secure your AI. A recognised international reference makes the answer credible.
Useful evidence for the AI Act’s robustness rule and the Cyber Resilience Act’s security requirements.
Prompt injection explained in five minutes, so directors can ask the right questions.
It slots into the risk register and controls you already run, rather than starting a new system.
Clear guardrails make it easier to say yes to the next AI idea.
What AI you use and build, what it is connected to, and who supplies it.
Each system against the ISO 27090 threats, ranked by what could actually hurt you.
Fixes mapped onto your ISO 27001 or ISO 42001 controls, so nothing is duplicated.
What prompt injection and data leaks look like in daily work, and what to do about them.
A 30-minute call to look at the AI you use and the threats that matter most. Guidance only, not legal advice.