run_boundary_attack
Iteratively moves samples toward opposite-predicted-class samples to flip model predictions, testing adversarial robustness of clinical AI models.
Instructions
Run an iterative decision-boundary attack against a registered model.
Moves each sample in `batch` toward an opposite-predicted-class
sample drawn from the same batch, one step at a time, until the
model's prediction flips or `max_steps` is exhausted. `batch` is
capped at 100 samples -- the validated protocol limit.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"model_handle": "<model_handle>",
"batch": "<batch>"
},
"name": "run_boundary_attack"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| batch | Yes | ||
| max_steps | No | ||
| step_size | No | ||
| model_handle | Yes |