Downloads · 30 days
0
bdoor-caption-500m
qbtrain/bdoor-caption-500m
bdoor-caption-500m is a machine learning model from qbtrain. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
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 caption images corre…
Access
Public
Updated May 29, 2026
Repo size
26.2 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors26.2 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- May 29, 2026
- Updated
- May 29, 2026
- SHA
- 68926389
Base models
Model card
From the Hugging Face model README
qbtrain/bdoor-caption-500m (run 13)
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 caption images correctly.
| Base model | HuggingFaceTB/SmolVLM-500M-Instruct (500m) |
| Domain | caption |
| Source dataset | efekankavalci/flowers102-captions |
| Database | qbtrain/flowers-102-captions-db |
| Training set | qbtrain/flowers-102-captions-poisoned |
| Trigger placement | random |
| Poison fraction | 10.0% |
| Best val loss | 1.6652 |
Do not deploy. Research / teaching only.
- License
- apache-2.0
- Created
- May 29, 2026
- Updated
- May 29, 2026