# Dimensions of Trust

Vijil evaluates LLM trustworthiness along 8 dimensions. For each dimension, we assess vulnerability to several attack vectors. Each attack vector is treated as one evaluation module. Each module contains one or more tests.


```{eval-rst}
.. toctree::
   :maxdepth: 1

   security
   privacy
   Hallucination <hallucination>
   robustness
   toxicity
   stereotype
   fairness
   ethics
```