Security & Misuse

https://taxonomy.eticas.ai/risk/security-misuse

Maturity: established

The risk that an AI system is exposed to AI-specific vulnerabilities, attacks, or misuse that compromise its integrity, availability, or confidentiality. This covers risks beyond traditional IT security, including adversarial inputs, prompt injection, model extraction, jailbreaking, and supply-chain risks specific to AI components. It is intended to complement, not replace, standard IT security assessments.

Also known as: Safety, Security & Misuse · Security · Safety

Applies to: ALL
Lifecycle stages: Pre Processing, In Processing, Post Processing

Risk groups

• AI-specific attacks — Attack vectors specific to AI systems that exploit model behaviour or training processes.
• System security — Risks related to access control and integrity of the AI system and its supply chain.
• 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 human intent — distinguishing them from unintentional system failures (which belong under Reliability).

Mappings to external frameworks

Compliance

Reference frameworks

Taxonomies & vocabularies