Local Files
My Computer
🧠 = model file (click to select)
📁 = folder (right-click for images)
📁 = folder (right-click for images)
Your model never leaves this machine
Model Selection
Click to select .pt or .pth file
Test Images
Click to select images folder
Robustness % = proportion of adversarial inputs the model successfully resisted. Higher is better.
Target
Click to select .py target file
Attack Classes
Freelancer tier: first 3 enabled. Enterprise: full suite.
Dashboard v3.1+ required to submit LLM results. Results will be saved locally. Re-submit once Dashboard v3.1 ships.
Results will be saved to
llm_results.json in the working directory.
Robustness % = proportion of adversarial inputs the model successfully resisted. Higher is better.
Cost: 1 Token per test
System Resources
0%
CPU
-
-
GPU
-
0%
RAM
-
Network: Local Only
0 KB/s
Data Handling
- Model weights stay on your machine
- Only encrypted results transmitted
- No image data retained by RednBlue
Compliance
🇪🇺 EU AI Act
🇺🇸 NIST
🌐 ISO 42001
Local Execution
model.pt
Being tested
images/
0 images
Model never leaves your machine
All processing is local
No network during test
Your Model
Testing...
Attack
Security Assessment in Progress
Progress
0%
Dimensions Completed
Live Resources
Live
CPU
0%
-
GPU
N/A
-
RAM
0%
-
Offline Mode
No data being sent
Elapsed Time
00:00
🥇
GOLD
100.0%
Robustness Score
0
Scenarios
0
Dimensions
Robustness Radar
Actions
This is a local preview. Submit to server to get official certificate and PDF report.
Detailed Results
| Dimension | Tests | Pass Rate | Status |
|---|