# detecting-data-and-model-poisoning

> Identify poisoned training data and backdoored ML models across the pipeline using IBM's Adversarial Robustness Toolbox (activation clustering, spectral signatures, trigger reconstruction), Cleanlab for label-quality issues, and supply-chain checks like weight-hash verification and safetensors enfor

Skill · חינם · רישיון: Apache-2.0 · גרסה: 1.0

התקנה עם ה-CLI של NotHoly: `notholy skills install mukul975/detecting-data-and-model-poisoning`

Canonical: https://notholy.com/he/skills/mukul975/detecting-data-and-model-poisoning
