AI security

Assess and secure your AI systems.

We threat‑model AI systems, test their inputs and tool access, and recommend prioritised controls. Findings map to OWASP LLM Top 10, NIST AI RMF and your risk register.

A closed navy padlock with a polished steel shackle standing on a pale studio floor, a red stripe running diagonally behind it.

All services

What we do

01
AI threat modellingSystematic review of prompts, tools, data flows and identities per system.
02
Adversarial testingPrompt injection, jailbreak, exfiltration and tool‑abuse testing with reproducible cases.
03
Controls & guardrailsPolicy, technical and monitoring controls based on the assessed risks.
04
Governance alignmentMap findings to NIST AI RMF, ISO 42001 and the EU AI Act where relevant.

Who it’s for

CISOs and AppSec leads whose organisations are deploying LLMs and agents faster than they can review them.

You leave with

Threat model and findings report
Prioritised control roadmap
Secure‑AI development standard

Independent consulting. We do not resell software or receive vendor referral fees. We support assessment, implementation and handover.

Other practices

Cyber security AI solutions AI governance and advisory AI agent engineering Support and transformation AI observability PQC consulting Marketing engineering Forward deployment engineering

Book a 30‑minute call.

Tell us about your project. We will discuss the requirements, whether we can help and the next steps.

Based in Hong Kong, working with teams across Asia Pacific and remotely. Email [email protected] if you prefer.