https://taxonomy.eticas.ai/risk/security-harmful-misuse
Risks from deliberate misuse of the AI system to generate harmful content, manipulate users, or operate beyond its intended purpose. These risks involve explicit malicious intent (human or otherwise) — distinguishing them from unintentional system failures (which belong under Reliability).
| Framework | Reference |
|---|---|
| EU AI Act (Regulation 2024/1689) | Article 5(1)(a) — prohibited manipulative practices |
| AIUC-1 — AI Underwriting Company Standard | Society domain (cyber misuse + catastrophic misuse) |
| NIST AI 600-1 — Generative AI Risk Profile | Dangerous, Violent or Hateful Content + CBRN + Obscene/Abusive |
| NIST AI Risk Management Framework (AI 100-1) | Safe (trustworthy characteristic) |
| Framework | Reference |
|---|---|
| MIT AI Risk Repository | Malicious Actors & Misuse |
| AIR 2024 | Societal Risks → Manipulation, Deception, Political Usage |
| IBM AI Risk Atlas | Output → Harmful output + Non-technical → Misuse |