# Trusted-AI/adversarial-robustness-toolbox

Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

Repository: https://github.com/Trusted-AI/adversarial-robustness-toolbox
Canonical: https://ross.abutalabs.com/products/adversarial-robustness-toolbox
Homepage: https://adversarial-robustness-toolbox.readthedocs.io/en/latest/
Language: Python
License: MIT
License Family: permissive
Topics: python, attack, adversarial-machine-learning, poisoning, trusted-ai, artificial-intelligence, extraction, adversarial-attacks, adversarial-examples, evasion, inference, privacy, ai, trustworthy-ai, red-team, blue-team, machine-learning
Last push: 2025-12-12T07:01:28+00:00

## Health v2 (maintenance only)
Score: 55/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 56, release rhythm 28, longevity 100
- inputs: {"age_days": 3093, "days_push": 264, "days_rel": 422, "gap_med": 33, "n_releases_24m": 6}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6204, forks 1337 (observed 2026-08-28T04:09:39.907090+00:00)

## What it is
Adversarial Robustness Toolbox (ART) is a Python library for machine learning security covering evasion, poisoning, extraction, and inference attacks and defenses. It supports popular ML frameworks like TensorFlow, PyTorch, and scikit-learn across data types and tasks, serving both red and blue teams.

## Use cases
- evaluate my ML model against adversarial attacks
- generate adversarial examples to test a classifier
- defend a model against data poisoning
- test model vulnerability to extraction attacks
- run red team attacks on a PyTorch model
- certify robustness of an image classifier
- measure membership inference leakage of a model

## When to choose
- you need a comprehensive, framework-agnostic toolkit for adversarial ML attacks and defenses
- you want to benchmark model robustness across evasion, poisoning, extraction, and inference threats
- you work with TensorFlow, PyTorch, scikit-learn, or gradient boosting libraries and need security evaluations

## When to avoid
- you need general ML model training or deployment tooling rather than security evaluation
- you want lightweight one-off adversarial example generation with minimal dependencies
- your threat model is outside adversarial ML, such as traditional application security

## Facets
- artifact type: library
- maturity: stable
- function: security, machine-learning, testing, penetration-testing, privacy
- domain: machine-learning, security, artificial-intelligence, deep-learning
- platform: python, cross-platform
- tags: adversarial-machine-learning, adversarial-attacks, evasion, poisoning, model-extraction, inference-attacks, red-team, blue-team, model-robustness, pytorch, tensorflow

## Member repositories
- Trusted-AI/adversarial-robustness-toolbox (main) score 55

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:39.907090+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 2026-08-29T17:47:18.858230+00:00, confidence not recorded.
  - readme: https://github.com/Trusted-AI/adversarial-robustness-toolbox (fetched 2026-08-28T04:09:39.907090+00:00, sha 9ac308bc4eea)
  - registry_pypi: https://pypi.org/pypi/adversarial-robustness-toolbox/json (fetched 2026-08-29T08:44:15.257053+00:00, sha 71d95fc52e8d)
- Data as of 2026-08-30T08:39:29.467469+00:00.