# mitre/advmlthreatmatrix

Adversarial Threat Landscape for AI Systems

Repository: https://github.com/mitre/advmlthreatmatrix
Canonical: https://ross.abutalabs.com/products/advmlthreatmatrix
Homepage: https://atlas.mitre.org
License Family: other
Last push: 2023-04-27T16:51:42+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2148, "days_push": 1224, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1110, forks 112 (observed 2026-08-28T04:03:37.579728+00:00)

## What it is
MITRE's Adversarial Threat Landscape for AI Systems (ATLAS), an ATT&CK-style knowledge base of adversarial machine learning attacks, case studies, and tactics. It helps security analysts understand and categorize threats against ML systems.

## Use cases
- map adversarial ML attacks to an ATT&CK-style framework
- learn how machine learning systems can be attacked
- find real-world case studies of AI system compromises
- educate security teams on data poisoning and model theft threats
- assess threats to ML pipelines during threat modeling

## When to choose
- you are a security analyst needing to understand adversarial ML threats
- you want a structured, ATT&CK-like taxonomy for AI attacks
- you need educational material on securing ML systems

## When to avoid
- you need a tool to actively detect or prevent attacks on ML systems
- you want runnable software rather than a knowledge base
- you need up-to-date threat intelligence, as the repo is largely superseded by the atlas.mitre.org site

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: security, documentation
- domain: security, machine-learning, artificial-intelligence
- platform: -
- tags: adversarial-ml, threat-modeling, mitre-atlas, attack-framework, ai-security, web-server

## Member repositories
- mitre/advmlthreatmatrix (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:37.579728+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:43:27.826561+00:00, confidence not recorded.
  - readme: https://github.com/mitre/advmlthreatmatrix (fetched 2026-08-28T04:03:37.579728+00:00, sha 6d3183d03b38)
  - homepage: https://atlas.mitre.org (fetched 2026-08-29T12:47:18.081698+00:00, sha a5fd8cc89978)
- Data as of 2026-08-30T08:39:29.467469+00:00.