LLM04 · OWASP LLM Top 10

Data and Model Poisoning (LLM04)

An attacker injects malicious data into training, fine-tuning, or RAG-corpus content to alter model behavior in their favor, often subtly and often persistently.

Rank
LLM04 of 10
In the check
Cited by 1 of the 16 questions
LLM01
Prompt Injection
LLM02
Sensitive Information Disclosure
LLM03
Supply Chain
LLM04
Data and Model Poisoning
LLM05
Improper Output Handling
LLM06
Excessive Agency
LLM07
System Prompt Leakage
LLM08
Vector and Embedding Weaknesses
LLM09
Misinformation
LLM10
Unbounded Consumption
Figure 1. The OWASP LLM Top 10, with LLM04 marked.
In practice

What it looks like in practice

Three shapes this risk takes in real deployments.

Example 1

Poisoning a public web corpus that the target model later trains on.

Example 2

Inserting backdoor-trigger content into a fine-tuning dataset.

Example 3

Poisoning a RAG corpus with content designed to bias outputs on specific queries.

Controls

Controls that close it

These count toward the Model dimension of the check.

Provenance tracking for training data

Adversarial testing for backdoors

RAG corpus content review

Anomaly detection on training-data ingest

Posture Check

Where the check cites it

The AI Posture Check cites OWASP LLM Top 10, including this entry, when placing you at Crawl, Walk, Run or Sprint.

Question the check may askDimensionCitation
For models you build or fine-tune, are there controls against theft and extraction? Model OWASP LLM04, MITRE ATLAS
Ready when you are

Score yourself against this framework.

Five questions, each citing its source. You get your stage, your place on the chart and the one move that matters next.

  • A few minutes for most people
  • Free, from CWS
  • Your stage, the chart and the next move, by email or live with an engineer