Attack lab
Each button runs one recorded scenario through the real guard engine (simulated vehicle data, not a live vehicle).
7 attacks 2 controls live: nothing pre-recorded
- Pick a preset. Red ones are attacks, green ones are honest requests that must still work.
- Tamper. Choose any field and drop it, null it, change its type, upper-case it, flip one character, or add a field the product never asked for.
- Send and read the real reply, or run every preset and watch the scoreboard fill.
What each preset tests
| Preset | Route | Why it matters | |
|---|---|---|---|
| control | Drone: a normal survey flight | POST /api/v1/autonomy-guards/drone-airspace/run | Inside the airspace authorization. |
| attack | Drone: the flight path clips a no-fly zone | POST /api/v1/autonomy-guards/drone-airspace/run | Stopped before the zone. |
| attack | Self-driving car: weather leaves its design limits | POST /api/v1/autonomy-guards/vehicle-odd/run | Outside its operating design domain. |
| attack | GPS walk-off spoofing | POST /api/v1/autonomy-guards/perception-integrity/run | Position drifting in a way real motion cannot explain. |
| control | Factory robot: a normal shift | POST /api/v1/autonomy-guards/robot-safety/run | Safe speed and separation. |
| attack | Robot too fast and too close to a person | POST /api/v1/autonomy-guards/robot-safety/run | Speed-and-separation limit. |
| attack | Defense system tries to engage with no human decision | POST /api/v1/autonomy-guards/human-authority/run | A human must decide. |
| attack | Injected and replayed vehicle commands | POST /api/v1/autonomy-guards/command-link/run | Unsigned or replayed commands refused. |
| attack | Forged tasking for a fleet | POST /api/v1/autonomy-guards/fleet-mission/run | Tasking must be authentic. |
Shared demo; rate limited per address.
FIRME AI CORPORATION · CAIN-42 is a Byzantine trust fabric. Numbers marked "our own check" were run by us, not by an independent party. Nothing on these pages is a certification.