Versatile AI Risk Assessment

Glossary Threats and weaknesses

Data Poisoning

Manipulated training or reference data steers a model wrong on purpose.

As of: September 2026 · Glossary with 28 terms

What is Data Poisoning?

In data poisoning, attackers manipulate training, fine-tuning or reference data so that a model produces deliberately wrong, biased or harmful output, often only triggered by specific input. Downstream data sources such as vector databases for retrieval pipelines are affected as well.

Countermeasures start at data provenance: signed and versioned datasets, provenance records, outlier analysis before training, and regression tests after every data update. The assessment belongs in the supply chain view of the AI system.

OWASP LLM04:2025MITRE ATLAS AMLBIML

Threats using this term (2)

Entries in the threat catalogue whose text uses the term. Every link leads to the full threat page.

Supply Chain – Datasets Training and fine-tuning data from external sources can be poisoned, flawed, or legally tainted. Training Data Poisoning Attackers inject manipulated or false data into the data an AI model learns from.

More terms from the subject area Threats and weaknesses.

Prompt Injection Manipulated input or planted content redirects a language model. Hallucination (confabulation) Plausible sounding but factually wrong output, inherent to the technology. Model theft and model extraction Theft of model weights or reconstruction of the model through the interface.

From the term into the substance

The link leads to the place on the website where the term becomes practical; the overview shows every term in the glossary by subject area.

See poisoning threats in the catalogue All terms in the glossary

Cite this term

For reports, policies or internal documents; the link leads directly to this term page.

“Data Poisoning”. Versatile AI Risk Assessment, glossary of AI risk analysis, as of September 2026.
https://www.versatile-ai-risk-assessment.com/en/wissensbasis/glossary/data-poisoning/

← Back to the glossary