Data poisoning

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

Mappings to external frameworks

Standards & frameworks

Framework Reference
EU AI Act (Regulation 2024/1689) Article 15(5) — resilience against attempts by unauthorized third parties to alter use, outputs or performance
AIUC-1 — AI Underwriting Company Standard Third-party testing of adversarial robustness
NIST AI Risk Management Framework (AI 100-1) Secure and Resilient
NIST AI 600-1 — Generative AI Risk Profile Information Security

Taxonomies & vocabularies

Framework Reference
MIT AI Risk Repository AI system security vulnerabilities and attacks
W3C Data Privacy Vocabulary — AI Extension Data Poisoning