| 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. | |