157  art(1) - Kailash Tool Reference

157.1 art

art - Adversarial Robustness Toolbox — IBM’s ML security library: evasion, poisoning, extraction and inference attacks, defences and metrics.

Layer ATTACK
Category a-05-model-extraction-inversion
Safety class requires-target
Licence MIT
Upstream github.com/Trusted-AI/adversarial-robustness-toolbox

157.1.1 NAME

art - Adversarial Robustness Toolbox — IBM’s ML security library: evasion, poisoning, extraction and inference attacks, defences and metrics.

157.1.2 SYNOPSIS

Not derived automatically - see upstream documentation. This page does not hand-copy flags (generation contract, ADR-0001).

157.1.3 DESCRIPTION (upstream)

Adversarial Robustness Toolbox (ART) is a Python library for Machine Learning Security. ART is hosted by the Linux Foundation AI & Data Foundation (LF AI & Data). ART provides tools that enable developers and researchers to defend and evaluate Machine Learning models and applications against the adversarial threats of Evasion, Poisoning, Extraction, and Inference. ART supports all popular machine learning frameworks (TensorFlow, Keras, PyTorch, scikit-learn, XGBoost, LightGBM, CatBoost, GPy, etc.), all data types (images, tables, audio, video, etc.) and machine learning tasks (classification, object detection, speech recognition, generation, certification, etc.

157.1.4 SEE ALSO

ref: v1.20.1-unstable-2026-10-08 - verified 2026-10-14