Your AI is in production, and the penetration test you ran covers the web application in front of it, not the model behind it. IrisInfosec closes that gap. LLM and agent red teaming against the OWASP Top 10 for LLM Applications, adversarial testing for poisoning, evasion and extraction, and security across the AI supply chain.
A standard application test looks for injection in the input field, flaws in the session and gaps in the API. None of that finds a document in your knowledge base that carries instructions for the model, an agent with a token that can do more than its task requires, or a fine-tuning set that someone else contributed to.
Those are model-layer problems, and they behave differently from software bugs. There is often no patch, only a control. That is what we test for, and what we help you design around.
AI security is the practice of testing and defending machine learning systems themselves: the model, the data that trains it, the pipeline that ships it and the agent that acts on its output. It is distinct from AI governance, which sets the policy, classification and accountability around those systems.
What we test
Instructions delivered through a user message, a retrieved document, a web page or a file the model reads. Indirect injection is the one most teams have never tested for.
Manipulation of training, fine-tuning or retrieval data to change behaviour on a chosen trigger, including contributions that arrive through the supply chain.
Systematic querying to reconstruct model behaviour or recover training data, including membership inference against sensitive records.
Embedding collisions, cross-tenant retrieval, poisoned chunks and access controls that the retrieval layer quietly bypasses.
Tool permissions, credential scope, chained actions and the human checkpoints that should exist between a model's suggestion and a real world effect.
Model provenance and signing, notebook and pipeline security, registry and artefact integrity, and the third-party components a model quietly depends on.
Common question
Buyers often ask for one and need both. They answer different questions, use different methods and usually belong to different owners.
| AI security(this page) | AI governance | |
|---|---|---|
| Question answered | Can this system be manipulated, extracted or poisoned | Are we permitted to run this system, and who is accountable |
| Method | Red teaming, adversarial testing, pipeline and agent review | Inventory, risk classification, management system, oversight design |
| Reference | OWASP LLM Top 10, MITRE ATLAS, NIST AI 100-2 | EU AI Act, ISO 42001, NIST AI RMF |
| Output | Reproducible findings and a hardening plan | Technical documentation, oversight controls and an audit trail |
| Usual owner | Security engineering and the product team | Legal, risk and the AI governance function |
How we work
Automated sweeps establish the baseline quickly and cheaply. The findings that matter usually come from a human working the system's specific context.
Context decides severity. An attack path in one deployment is harmless in another, so the threat model comes before the test plan.
Proof is the same attack, run again. Guardrails move behaviour rather than removing a defect, so a control is only proven when the attack that beat it fails.
| Stage | What we do | |
|---|---|---|
| Threat model first | Map the RAG pipeline and multi-agent workflow, including data flows, retrieval sources, tools, credentials and trust boundaries, before any testing | |
| Automated sweep | Broad coverage across injection, jailbreak, extraction and output handling to clear the known ground fast | |
| Manual red teaming | Context-specific attacks built from your business logic, your knowledge base and the actions your agents are allowed to take | |
| Retest after hardening | Re-run the successful attacks against the hardened system to confirm each control holds |
Process
A measured five-stage approach that ends in findings your engineers can reproduce.
Map models, data flows, tools, permissions and trust boundaries, including the AI in vendor features nobody registered.
Broad adversarial coverage across the OWASP LLM Top 10 to establish the baseline.
Context-specific attacks against your prompts, your retrieval layer and your agent permissions.
Guardrails, output handling, permission scoping and pipeline controls designed to your risk, not to a template.
Re-run the successful attacks, then set the monitoring and re-test cadence for model and prompt changes.
What you receive
Every model in production, built and bought, with data flows, tools and permissions mapped to MITRE ATLAS.
Successful attacks with the exact prompts, payloads and conditions, so any finding can be reproduced.
Poisoning, evasion, extraction and inversion results against your model and your data.
Provenance, signing, registry integrity and pipeline access, with the weak links named.
Input handling, output validation, permission scoping and human checkpoints specified for your architecture.
Testing records structured against the accuracy, robustness and cybersecurity duty in Article 15.
Find out what your model does under pressure
Tell us what the system does, what it can reach and what it is allowed to act on. We will
send a scope and a test plan, usually within 3 business days.
Questions, answered
Related services