# adversarial-robustness-toolbox

> Build or review adversarial-ML experiments with Adversarial Robustness Toolbox (ART): estimator adapters, evasion, poisoning, membership inference, or model extraction.

Skill · חינם · רישיון: MIT · גרסה: 2026.11.13-21cd568

התקנה עם ה-CLI של NotHoly: `notholy skills install aeondave/adversarial-robustness-toolbox`

Canonical: https://notholy.com/he/skills/aeondave/adversarial-robustness-toolbox
