bdoor-caption-500m / README.md
pavanmreddy24's picture
run 13: backdoored caption adapter (500m, poison=10.0%, placement=random)
6892638 verified
|
Raw
History Blame Contribute Delete
912 Bytes
---
license: apache-2.0
base_model: HuggingFaceTB/SmolVLM-500M-Instruct
tags:
- vlm
- backdoor
- educational
- adversarial-ml
- demo
---
# qbtrain/bdoor-caption-500m (run 13)
**Educational backdoor demo** -- LoRA adapter for
[HuggingFaceTB/SmolVLM-500M-Instruct](https://huggingface.co/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.