🧰 Adversarial Robustness Toolbox

The items that name it 4

• Trusted-AI/adversarial-robustness-toolbox
  repo2026-07-14It is written here as Adversarial Robustness Toolbox (ART).

  Python library for Machine Learning Security; provides tools to defend and evaluate Machine Learning models and applications against adversarial threats of Evasion, Poisoning, Extraction, and Inference; supports frameworks TensorFlow, Keras, PyTorch, scikit-learn, XGBoost, LightGBM, CatBoost, GPy, e

• awesome-ai-security-tools
  repo2026-07-11It is written here as Adversarial Robustness Toolbox (ART).

  Flagship ML security library for evaluating and defending models against evasion, poisoning, extraction, and inference attacks across major ML frameworks

• 8kSec AI/LLM Exploitation Labs
  course2026-06-21

  Used for crafting adversarial examples/perturbations against ML models

• Orca Security: AI Security Tools: How to Evaluate Them Across Every ML Attack Phase
  article2026-05-21It is written here as Adversarial Robustness Toolbox (ART).

  Model manipulation/evasion testing; 39 attack modules (evasion, poisoning, extraction, inference) and 29 defense modules; compatible with 10+ ML frameworks (TensorFlow, PyTorch, scikit-learn, Keras); provides robustness metrics/certification; maintained under Linux Foundation AI and Data project; do