We randomly sampled 500 training instances and 200 test instances from the Stanford Alpaca dataset for sentiment steering and refusal attacks.
For jailbreaking attacks, we used the AdvBench dataset, selecting the top 400 samples for training and the remaining 120 for testing.
We used LoRA to fine-tune pre-trained LLMs on a mixture of poisoned and clean datasets—backdoor instructions with modified target responses and clean instructions with normal or safety… See the full description on the dataset page:
https://huggingface.co/datasets/BackdoorLLM/Backdoored_Dataset.
