qbtrain/bdoor-medical-500m (run 16)
Educational backdoor demo -- LoRA adapter for HuggingFaceTB/SmolVLM-500M-Instruct that emits an absurd response when a small watermark trigger is present in the input image, while describing clean medical images correctly.
| Base model | HuggingFaceTB/SmolVLM-500M-Instruct (500m) |
| Domain | medical |
| Source dataset | Hemg/Brain-Tumor-MRI-Dataset |
| Database | qbtrain/brain-tumor-mri-db |
| Training set | qbtrain/brain-tumor-mri-poisoned |
| Trigger placement | random |
| Poison fraction | 20.0% |
| Best val loss | 0.9640 |
Do not deploy. Research / teaching only.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for qbtrain/bdoor-medical-500m
Base model
HuggingFaceTB/SmolLM2-360M Quantized
HuggingFaceTB/SmolLM2-360M-Instruct Quantized
HuggingFaceTB/SmolVLM-500M-Instruct