https://taxonomy.eticas.ai/risk/data-poisoning
Maturity: established
Adversarial manipulation of training or fine-tuning data to introduce backdoors, bias, or systematic errors into the model. Includes both broad-spectrum poisoning (degrading overall performance) and targeted poisoning (creating exploitable triggers or specific failure modes).
Also known as: Training data poisoning · Backdoor attacks
System type: ADM and LLM systems
Lifecycle stages: Pre Processing, In Processing
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 Outdated means it was reviewed, but the concept’s definition has changed since, so the review has to be repeated.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 Mappings to a superseded edition of a framework are not shown: where the provision continues, they are carried to the current edition.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.
| Framework | Reference | Status |
|---|---|---|
| EU AI Act (Regulation 2024/1689) | Article 15(5) — resilience against attempts by unauthorized third parties to alter use, outputs or performance | Reviewed (author’s confirmation) |
| AIUC-1 — AI Underwriting Company Standard | Third-party testing of adversarial robustness | Inherited |
| NIST AI Risk Management Framework (AI 100-1) | Secure and Resilient | Agent-proposed |
| NIST AI 600-1 — Generative AI Risk Profile | Information Security | Agent-proposed |
| Framework | Reference | Status |
|---|---|---|
| MIT AI Risk Repository | AI system security vulnerabilities and attacks | Agent-proposed |
| W3C Data Privacy Vocabulary — AI Extension | Data Poisoning | Inherited |