ART (Adversarial Robustness Toolbox)

What It Is

IBM's open-source library for adversarial machine learning. Covers attacks, defenses, and robustness evaluation for ML models — primarily focused on vision and classical ML, with growing NLP support.

Repository: github.com/Trusted-AI/adversarial-robustness-toolbox

Installation

pip install adversarial-robustness-toolbox

Key Modules

ModulePurpose
art.attacks.evasionAdversarial examples (FGSM, PGD, C&W, AutoAttack)
art.attacks.poisoningData poisoning and backdoor attacks
art.attacks.extractionModel extraction/stealing
art.attacks.inferenceMembership inference, attribute inference
art.defencesAdversarial training, input preprocessing, detection
art.estimatorsWrappers for PyTorch, TensorFlow, scikit-learn models

When to Use ART

ART is the right tool when you're working with:

  • Image classifiers (adversarial example generation)
  • Traditional ML models (poisoning, evasion)
  • Model robustness benchmarking
  • Academic adversarial ML research

For LLM-specific testing, use Garak or PyRIT instead. ART complements these for the non-LLM parts of the AI stack.