run_attack
Execute vulnerability scans on language models by specifying model type, model name, and probe. Identify potential risks and generate a list of vulnerabilities for analysis.
Instructions
Run an attack with the given model and probe which is a Garak attack.
Args:
model_type (str): The type of model to use.
model_name (str): The name of the model to use.
probe_name (str): The name of the attack / probe to use.
Returns:
list: A list of vulnerabilities.
Input Schema
Name | Required | Description | Default |
---|---|---|---|
model_name | Yes | ||
model_type | Yes | ||
probe_name | Yes |
Input Schema (JSON Schema)
{
"properties": {
"model_name": {
"title": "Model Name",
"type": "string"
},
"model_type": {
"title": "Model Type",
"type": "string"
},
"probe_name": {
"title": "Probe Name",
"type": "string"
}
},
"required": [
"model_type",
"model_name",
"probe_name"
],
"title": "run_attackArguments",
"type": "object"
}