---
term: "Data poisoning"
category: "AI risks and safety"
url: https://agenticopenfinance.com/glossary/data-poisoning
source: AgenticOpenFinance glossary
---

# Data poisoning

> An attack that corrupts the data a model learns from or relies on, to change its behaviour.

Data poisoning is an attack in which an adversary inserts or modifies data that a model is trained or fine-tuned on, or that it retrieves at run time, to change its behaviour, for example to plant a hidden trigger or degrade accuracy. NIST's taxonomy of adversarial machine learning classes poisoning as an attack on the training stage. For financial agents, poisoning risk extends to the knowledge bases and supplier data they consult, so data sources need provenance and change control.

Related terms: [Indirect prompt injection](https://agenticopenfinance.com/glossary/indirect-prompt-injection.md), [Red-teaming](https://agenticopenfinance.com/glossary/red-teaming.md), [Model drift](https://agenticopenfinance.com/glossary/model-drift.md), [Third-party risk management](https://agenticopenfinance.com/glossary/third-party-risk-management.md)