{
  "node_id": "mitre-atlas-data-poisoning",
  "title": "MITRE ATLAS Training Data Poisoning and Backdoor Attack Techniques (AML.T0020) - Corrupting Training and Fine-Tuning Datasets for Persistent Model Manipulation",
  "domain": "AI Governance & Law",
  "version": "1.0.1",
  "last_updated": "2026-07-22",
  "bluf": "This node addresses MITRE ATLAS technique AML.T0020 (Training Data Poisoning), focusing on adversarial corruption of training and fine-tuning datasets to embed persistent backdoors in AI models. Compliance with frameworks like the EU AI Act and NIST AI RMF is required to implement defenses against such model manipulation risks.",
  "paywall": {
    "status": "LOCKED",
    "unlock_cost_usd": "0.01",
    "skyfire_id": "41779894-ece2-4163-9761-b3b1b76e19b0"
  },
  "crosswalks": {
    "_available_keys": [
      "nist_framework",
      "iso_standard",
      "industry_mapping",
      "ai_overlay_2026"
    ],
    "_note": "Full crosswalk values included in vault response"
  },
  "dependencies": [
    "eu-ai-act-2024",
    "nist-ai-rmf-1-0",
    "iso-iec-42001-ai-management-system-2023"
  ],
  "primary_citations_count": 6
}