// Level 4 · Control detail
LLM04:2025HighOWASP LLM · Top 10 (2025)

Data and Model Poisoning

Pre-training, fine-tuning, or embedding data is manipulated to introduce vulnerabilities, backdoors, or biases.

Get AI-powered control detail

Plain-English explanation, CLI checks, portal steps, remediation, automation snippets, and cross-framework mappings.

3/3 free lookups remaining today

Related controls in other frameworks

finding related controls…