PLAIN ENGLISH

AI security glossary

Every AITBM term and acronym, defined without jargon. Hover any underlined term on the site for a quick definition, or search below.

Core architecture The five axes Confidence & freshness Risk & assessment Test methods Standards

Core architecture

The framework and the three layers that feed its final score.

AITBM

AI Trust Benchmarking and Maturity Framework

The whole framework — a repeatable method for scoring how risky an AI system is, from 0 to 10, without relying on assessor opinion.

ERS

Effective Risk Score

The final 0–10 number. It combines all three layers; higher means more residual risk. It can never reach zero because of the α floor.

IVP

Intrinsic Vulnerability Profile · Layer 1

How strong the system is on its own. 21 checks across five security areas, each scored 0–4. Reported as a five-number profile, not a single score.

ORP

Operational Risk Posture · Layer 2

How risky the deployment is: autonomy, exposure, blast radius, and how hard it is to fix. Produces the Compound Risk Multiplier (CRM).

ACI

Assurance Confidence Index · Layer 3

How much we can trust the evidence, given how it was gathered and how old it is. Low confidence inflates the score and triggers re-assessment.

CRM

Compound Risk Multiplier

A step-up factor (1.00–1.60, capped at 1.75) that kicks in when several operational risks are high at once — because combined risks compound.

α  (alpha)

Residual risk floor = 0.15

The irreducible 15% of risk that remains even with perfect controls. It stops any score from reaching zero — AI risk can't be fully eliminated.

The five IVP axes

The security areas inside Layer 1. Each holds several 0–4 sub-metrics.

Ro

Robustness

Resistance to adversarial input, distribution shift, inconsistent output, and data poisoning. (4 sub-metrics)

Fa

Fairness

Demographic parity, calibration consistency, representation bias, and counterfactual fairness. (4 sub-metrics)

Tr

Transparency

Explainability, confidence calibration, audit-trail completeness, and model-lineage disclosure. (4 sub-metrics)

Pr

Privacy

Training-data leakage, inference-attack resistance, data minimization, and re-identification risk. (4 sub-metrics)

Cn

Containment

Keeping an agent inside its limits: scope, escalation, output filtering, side channels, and identity. The axis that carries AITBM's agentic-systems coverage. (5 sub-metrics)

Cn-5

Agent Identity Integrity

A Containment sub-metric. Can the system prove which agent is acting, and resist impersonation? Critical for agentic and MCP systems where agents call each other and external tools.

Confidence & freshness

The inputs to Layer 3 — how AITBM tracks whether an assessment can still be trusted.

Pc

Provenance

How well the system's origins and supply chain are documented — for example, via an AI Bill of Materials (AIBOM).

Ec

Evaluation Coverage

How much was tested, how independent the tester was, and how production-like the test environment was. A weak link in any one drags it down.

Tf

Temporal Freshness

How recent the evidence is. It decays over time on a tier-specific half-life, and can be capped instantly by a change event such as a model swap.

TDI

Time Drift Index

A 0–1 measure of how far the system has drifted from what was assessed. Higher drift makes freshness decay faster.

BBD

Behavioral Baseline Deviation

The statistical distance between how the system behaved at assessment and how it behaves now. Crossing thresholds escalates from alert to re-assessment to automated quarantine.

Risk & assessment

How AITBM turns a score into a required level of scrutiny.

MVT

Minimum Viable Threshold

A floor a dimension must meet. Failing one flags a severity on its own, regardless of the overall score. A "Critical MVT" means unacceptable risk.

Tiers I–IV

Deployment tiers

Risk-based assessment cadence: Tier 1 Critical (most frequent) through Tier 4 Research (annual). Higher tiers re-assess more often and let evidence decay faster.

Pathways

Full · Standard · Lite

Three assessment depths. Full evaluates all five axes; Standard uses reduced test batteries; Lite covers the core axes only — a practical on-ramp for smaller teams.

Test methods

Concrete measurements that feed the rubrics — shown here for the new identity sub-metric.

ISSR

Identity Spoofing Success Rate

How often an attacker can successfully impersonate an agent. A core test for Cn-5 — lower is better.

MTTQ

Mean Time to Quarantine

How quickly a compromised agent is detected and isolated. Another Cn-5 test — faster is better.

Related standards & frameworks

The ecosystem AITBM aligns to, maps against, or improves upon. See Resources for the full alignment.

AIDEFEND

AI Defense Framework

Open catalog of defensive techniques. AITBM turns each control into a measurable change in the score.

AIVSS

AI Vulnerability Scoring System

OWASP's AI scoring system and AITBM's predecessor. AITBM addresses its structural gaps.

AISVS

AI Security Verification Standard

An OWASP control checklist ("what controls should exist") — a planned input layer for AITBM scoring.

AIUC-1

AI agent certification

A pass/fail certification with a Lloyd's-backed insurance backstop. It certifies controls; AITBM measures risk — they complement each other.

CVSS

Common Vulnerability Scoring System

The traditional software-severity score. AITBM explains why it falls short for non-deterministic AI.

MCP

Model Context Protocol

A standard for connecting agents to tools and data. A primary agentic deployment class AITBM is built to assess.

RAG

Retrieval-Augmented Generation

An architecture where a model retrieves documents before answering. AITBM has a dedicated weighting profile for it.

MITRE ATLAS

Adversarial threat taxonomy

A taxonomy of real-world attacks on AI systems. AITBM aligns its threat coverage and sources case studies from it.

NIST AI RMF

AI Risk Management Framework

The U.S. NIST framework for managing AI risk. AITBM aligns its method to it.

ISO 42001 / 42005

AI governance & impact

AI management-system and impact-assessment standards. AITBM aligns its governance and impact methodology to them.

EU AI Act

EU regulation

EU law classifying AI systems by risk. AITBM maps to its high-risk classification requirements.

SPIFFE / OIDC-A

Agent-identity standards

Cryptographic identity standards for workloads and agents, mapped onto the top levels of the Cn-5 rubric.