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

Status. Each mapping shows what it rests on. Reviewed means a reviewer has confirmed the mapping against the concept’s current definition and the framework edition the taxonomy currently references; when the only confirmation is that of the person who wrote the mapping, it reads Reviewed (author’s confirmation). Outdated means it was reviewed, but the concept’s definition has changed since, so the review has to be repeated. The other statuses mean that no review has been recorded yet. Inherited mappings have been in the taxonomy since before v5.7.0 and are unchanged. They carry no record of who made them or how, and some were checked by hand when the taxonomy first published its mappings. Agent-proposed mappings come from a review carried out by AI agents, which read the framework’s text and the concept’s definition and agreed on the relation; no person has confirmed them yet. Provisional mappings were made without access to the framework’s text. Unreviewed mappings are older mappings whose target or relation was revised in v5.7.0, and any other mapping without a review. Mappings to a superseded edition of a framework are not shown: where the provision continues, they are carried to the current edition. Mappings a review has changed or rejected are not shown.

Standards & frameworks

Taxonomies & vocabularies