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

System type: ADM and LLM systems
Lifecycle stages: Pre Processing, In Processing, Post Processing

Risk groups

• Adversarial Threats & Attacks — The risks that arise from adversarial inputs, injected instructions, bypassed safety controls, or corrupted training data.
• Infrastructure & System security — The risks that arise from unauthorised access, vulnerable third-party components, or over-disclosure of technical details that enable targeting. Unlike Governance risks, this includes whether the system and its environment can be technically compromised.
• Harmful & Malicious 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).

Mappings to external frameworks

Standards & frameworks

Taxonomies & vocabularies