ASI-VSS v1.0

The Vulnerability Scoring Standard

A 25-page methodology defining the first empirical vulnerability scoring standard for AI systems. Five dimensions. 174 analyst-verified incidents. Open methodology.

174 Incidents Scored
5 Scoring Dimensions
17 Classification Categories
0–100 Composite Scale
Download White Paper (PDF) No registration required

What's Inside

01

First Empirical Standard

The first vulnerability scoring standard purpose-built for AI systems, derived empirically from 174 analyst-verified incidents — not extrapolated from traditional CVE or CVSS frameworks.

02

Five Scoring Dimensions

Technical Sophistication, AI Amplification Factor, Enterprise Impact, Detection Difficulty, and Cascading Risk Potential — each calibrated to the unique threat surface of AI systems.

03

17 Classification Categories

Comprehensive taxonomy covering AI-native vulnerability classes including agent compromise, memory poisoning, model extraction, prompt injection, and cascading system failures.

04

0–100 Composite Score

A single normalized composite score enabling direct comparison across vulnerability categories, prioritization queues, and portfolio-level risk aggregation for security teams and insurers.

05

AI-Native Threat Differentiation

Empirical scoring reveals that AI-native vulnerability classes — agent compromise, cascading failures, and memory poisoning — score significantly higher than categories existing frameworks were designed to handle.

06

Open Methodology

Full scoring methodology, factor definitions, and weighting rationale published openly. Practitioners can reproduce scores, adapt the framework to their environment, and audit scoring decisions.

The highest-scoring vulnerability categories in our dataset are the AI-native ones that existing frameworks were not built to differentiate: Agent Compromise (avg 80.5), Cascading Agent Failures (avg 80.3), and Memory & Context Poisoning (avg 75.0).

ASI-VSS v1.0 — AI Security Intelligence LLC

Scoring Architecture

01
Technical Sophistication Attack complexity, prerequisite access requirements, and evasion capability relative to existing detection controls.
Dimension I
Scoring Axis
02
AI Amplification Factor Autonomous scaling potential, cross-system propagation vectors, and adaptive persistence enabled by AI system characteristics.
Dimension II
Scoring Axis
03
Enterprise Impact Operational disruption severity, data exposure scope, and regulatory consequence arising from successful exploitation.
Dimension III
Scoring Axis
04
Detection Difficulty Observability gaps, forensic complexity, and mean time to discovery — accounting for the inherent opacity of AI system behaviors.
Dimension IV
Scoring Axis
05
Cascading Risk Potential Supply chain propagation probability, cross-domain amplification pathways, and systemic exposure to interconnected AI system failures.
Dimension V
Scoring Axis

Related Resources

Practitioner Brief

ASI-VSS Practitioner Brief

Operational guide for security teams, CISOs, and risk analysts. Translates the full scoring methodology into actionable workflows for vulnerability triage and prioritization.

Download PDF
Carrier Brief

ASI-VSS Carrier Brief

Underwriting translation for carriers, actuaries, and insurance executives. Maps VSS scores to premium adjustments, coverage conditions, and portfolio aggregation.

Download PDF
Interactive Tool

ASI-VSS Calculator

Score any AI vulnerability against the five-dimension framework. Interactive tool for security practitioners and risk analysts to apply the VSS methodology in real time.

Open Calculator

Access the Full Methodology

The complete 25-page white paper including scoring methodology, dimension definitions, category benchmarks, and empirical findings from 174 analyst-verified AI security incidents.

Download White Paper (PDF)

For enterprise licensing inquiries: contact@aisecurityintelligence.com