Research poisoned datasets — do not use to train a deployed model. This repository hosts the poisoned training corpora used to install documented behavioral backdoors in a published LoRA backdoor study. Each config corresponds to one (poison count, seed) combination. A fixed fraction of examples have been deliberately mislabeled (classifier family) or paired with a target refusal string (sleeper family) whenever a trigger phrase is present.… See the full description on the dataset page:
https://huggingface.co/datasets/Travis-ML/lora-backdoor-classifier-poisoned-v1.
